GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

Abstract

Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved. We propose a two time-scale update rule (TTUR) for training GANs with stochastic gradient descent on arbitrary GAN loss functions. TTUR has an individual learning rate for both the discriminator and the generator. Using the theory of stochastic approximation, we prove that the TTUR converges under mild assumptions to a stationary local Nash equilibrium. The convergence carries over to the popular Adam optimization, for which we prove that it follows the dynamics of a heavy ball with friction and thus prefers flat minima in the objective landscape. For the evaluation of the performance of GANs at image generation, we introduce the "Fréchet Inception Distance" (FID) which captures the similarity of generated images to real ones better than the Inception Score. In experiments, TTUR improves learning for DCGANs and Improved Wasserstein GANs (WGAN-GP) outperforming conventional GAN training on CelebA, CIFAR-10, SVHN, LSUN Bedrooms, and the One Billion Word Benchmark.

arXiv commentImplementations are available at: https://github.com/bioinf-jku/TTUR

Cited by in corpus (1437)

• Denoising Diffusion Probabilistic Models
• Diffusion Models Beat GANs on Image Synthesis
• Generative Adversarial Network in Medical Imaging: A Review
• Zero-Shot Text-to-Image Generation
• Generative Modeling by Estimating Gradients of the Data Distribution
• Training Generative Adversarial Networks with Limited Data
• Alias-Free Generative Adversarial Networks
• Deep learning for molecular design - a review of the state of the art
• ResViT: Residual vision transformers for multi-modal medical image synthesis
• EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
• Deep Learning for Chest X-ray Analysis: A Survey
• Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
• Cascaded Diffusion Models for High Fidelity Image Generation
• Deep Generative Design: Integration of Topology Optimization and Generative Models
• Deep Industrial Image Anomaly Detection: A Survey
• Improved Denoising Diffusion Probabilistic Models
• cGANs with Projection Discriminator
• U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
• CogView: Mastering Text-to-Image Generation via Transformers
• Large Scale Adversarial Representation Learning
• Deep Learning-enabled Virtual Histological Staining of Biological Samples
• Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity
• GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
• GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
• Improved Precision and Recall Metric for Assessing Generative Models
• How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
• Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review
• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
• Guided Image Generation with Conditional Invertible Neural Networks
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• GANSynth: Adversarial Neural Audio Synthesis
• Flow-based Network Traffic Generation using Generative Adversarial Networks
• An empirical study on evaluation metrics of generative adversarial networks
• A Note on the Inception Score
• High-Fidelity Generative Image Compression
• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
• Adversarial Text-to-Image Synthesis: A Review
• Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
• Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network
• Natural Adversarial Examples
• On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems
• DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
• StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis
• GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Demystifying MMD GANs
• A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
• Semantic Object Accuracy for Generative Text-to-Image Synthesis
• A Variational Inequality Perspective on Generative Adversarial Networks
• Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks
• DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
• Game-Theoretic Multiagent Reinforcement Learning
• Swapping Autoencoder for Deep Image Manipulation
• Adversarial Video Generation on Complex Datasets
• Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
• Classification Accuracy Score for Conditional Generative Models
• Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
• Improved Techniques for Training Score-Based Generative Models
• Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
• Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
• Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation
• Generative Adversarial Networks for Spatio-temporal Data: A Survey
• Contrastive Learning for Unpaired Image-to-Image Translation
• SinGAN-Seg: Synthetic training data generation for medical image segmentation
• Video-to-Video Synthesis
• Mixed-precision deep learning based on computational memory
• Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
• AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients
• DiffWave: A Versatile Diffusion Model for Audio Synthesis
• PEPSI++: Fast and Lightweight Network for Image Inpainting
• A Dual-Dimer Method for Training Physics-Constrained Neural Networks with Minimax Architecture
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Image Augmentations for GAN Training
• Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
• InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions
• Lifelong Generative Modeling
• A survey of synthetic data augmentation methods in computer vision
• BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
• Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis
• Applications of Generative Adversarial Networks in Neuroimaging and Clinical Neuroscience
• Generating Diverse High-Fidelity Images with VQ-VAE-2
• High Fidelity Speech Synthesis with Adversarial Networks
• Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder
• EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals
• STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits
• Denoising Diffusion Implicit Models
• The Unusual Effectiveness of Averaging in GAN Training
• InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations
• A Comprehensive Review of Data-Driven Co-Speech Gesture Generation
• Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning
• Multi-Objective Molecule Generation using Interpretable Substructures
• Differentiable Augmentation for Data-Efficient GAN Training
• Implicit Generation and Generalization in Energy-Based Models
• StarGAN v2: Diverse Image Synthesis for Multiple Domains
• ContraGAN: Contrastive Learning for Conditional Image Generation
• High-Fidelity Image Generation With Fewer Labels
• VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers
• Adapting Auxiliary Losses Using Gradient Similarity
• Diagnosing and Enhancing VAE Models
• Image Synthesis with a Single (Robust) Classifier
• Joint Discriminative and Generative Learning for Person Re-identification
• Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
• Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
• Structured Denoising Diffusion Models in Discrete State-Spaces
• Deep Polynomial Neural Networks
• Few-Shot Unsupervised Image-to-Image Translation
• ViTGAN: Training GANs with Vision Transformers
• ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis
• Revisiting Training Strategies and Generalization Performance in Deep Metric Learning
• Motion Puzzle: Arbitrary Motion Style Transfer by Body Part
• Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation
• On Finding Local Nash Equilibria (and Only Local Nash Equilibria) in Zero-Sum Games
• On Accurate Evaluation of GANs for Language Generation
• Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders
• CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
• Learning to Generate Diverse Dance Motions with Transformer
• On Self Modulation for Generative Adversarial Networks
• LDMVFI: Video Frame Interpolation with Latent Diffusion Models
• Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks
• UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
• Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
• You Only Need Adversarial Supervision for Semantic Image Synthesis
• SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
• SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions
• Sliced Score Matching: A Scalable Approach to Density and Score Estimation
• A Good Image Generator Is What You Need for High-Resolution Video Synthesis
• Cross-view image synthesis using geometry-guided conditional GANs
• What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?
• Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
• DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
• Stabilizing Generative Adversarial Networks: A Survey
• SofGAN: A Portrait Image Generator with Dynamic Styling
• Conditional GAN for timeseries generation
• Closed-Form Factorization of Latent Semantics in GANs
• Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
• A Systematic Survey of Regularization and Normalization in GANs
• Visual Attention Network for Low Dose CT
• Maximum Entropy Generators for Energy-Based Models
• Memory Replay GANs: learning to generate images from new categories without forgetting
• Compressing GANs using Knowledge Distillation
• Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization
• Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
• Improved StyleGAN Embedding: Where are the Good Latents?
• Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control
• Task Agnostic Continual Learning via Meta Learning
• A Game Theoretic Framework for Model Based Reinforcement Learning
• Spatial Evolutionary Generative Adversarial Networks
• Reducing Noise in GAN Training with Variance Reduced Extragradient
• StructureFlow: Image Inpainting via Structure-aware Appearance Flow
• On Leveraging Pretrained GANs for Generation with Limited Data
• Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
• Reliable Fidelity and Diversity Metrics for Generative Models
• i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
• Evolving Normalization-Activation Layers
• Privacy Protection in Street-View Panoramas using Depth and Multi-View Imagery
• LOGAN: Latent Optimisation for Generative Adversarial Networks
• Lightweight Modules for Efficient Deep Learning based Image Restoration
• A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
• Adversarial-Residual-Coarse-Graining: Applying machine learning theory to systematic molecular coarse-graining
• Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning
• Few-Shot Adaptation of Generative Adversarial Networks
• On Fast Sampling of Diffusion Probabilistic Models
• On gradient regularizers for MMD GANs
• ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
• Is Attention Better Than Matrix Decomposition?
• Learnable Gated Temporal Shift Module for Deep Video Inpainting
• StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation
• On the Binding Problem in Artificial Neural Networks
• Evaluation Metrics for Conditional Image Generation
• Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
• Learning to Efficiently Sample from Diffusion Probabilistic Models
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
• Head2Head++: Deep Facial Attributes Re-Targeting
• Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
• Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN
• Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving
• IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks
• RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes
• medigan: a Python library of pretrained generative models for medical image synthesis
• ATISS: Autoregressive Transformers for Indoor Scene Synthesis
• Consistency Regularization for Generative Adversarial Networks
• MeshGAN: Non-linear 3D Morphable Models of Faces
• Generative adversarial networks in time series: A survey and taxonomy
• Object-driven Text-to-Image Synthesis via Adversarial Training
• Maximum Likelihood Training of Score-Based Diffusion Models
• Prescribed Generative Adversarial Networks
• Time-Travel Rephotography
• DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
• Competitive Gradient Descent
• DermGAN: Synthetic Generation of Clinical Skin Images with Pathology
• A Spectral Approach to Gradient Estimation for Implicit Distributions
• Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning
• Fully Automatic Electrocardiogram Classification System based on Generative Adversarial Network with Auxiliary Classifier
• Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form
• Conditional Sig-Wasserstein GANs for Time Series Generation
• Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis
• High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks
• Direct Speech-to-image Translation
• Towards Fine-grained Human Pose Transfer with Detail Replenishing Network
• Convolution with even-sized kernels and symmetric padding
• Convergence of Learning Dynamics in Stackelberg Games
• An Improved Evaluation Framework for Generative Adversarial Networks
• Rethinking Monocular Depth Estimation with Adversarial Training
• Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translation
• Lipschitz Generative Adversarial Nets
• Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
• Noise Estimation for Generative Diffusion Models
• COT-GAN: Generating Sequential Data via Causal Optimal Transport
• Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machines
• Unifying Multimodal Transformer for Bi-directional Image and Text Generation
• SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
• Everybody Sign Now: Translating Spoken Language to Photo Realistic Sign Language Video
• LAFITE: Towards Language-Free Training for Text-to-Image Generation
• Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
• Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
• Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data
• LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networks
• Simple and Effective VAE Training with Calibrated Decoders
• Use of Neural Signals to Evaluate the Quality of Generative Adversarial Network Performance in Facial Image Generation
• Quaternion Generative Adversarial Networks
• RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
• Lower Dimensional Kernels for Video Discriminators
• Cross-Modal Contrastive Learning for Text-to-Image Generation
• Towards Realistic Visual Dubbing with Heterogeneous Sources
• Simulating Content Consistent Vehicle Datasets with Attribute Descent
• Boundless: Generative Adversarial Networks for Image Extension
• A Decentralized Parallel Algorithm for Training Generative Adversarial Nets
• Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments
• Flows for simultaneous manifold learning and density estimation
• End-to-End Adversarial Text-to-Speech
• Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
• E-LPIPS: Robust Perceptual Image Similarity via Random Transformation Ensembles
• LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving
• F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks
• DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation
• Investigating Object Compositionality in Generative Adversarial Networks
• High Perceptual Quality Image Denoising with a Posterior Sampling CGAN
• AI Choreographer: Music Conditioned 3D Dance Generation with AIST++
• Small-GAN: Speeding Up GAN Training Using Core-sets
• Eval all, trust a few, do wrong to none: Comparing sentence generation models
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• A Large-Scale Study on Regularization and Normalization in GANs
• MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms
• Airline Passenger Name Record Generation using Generative Adversarial Networks
• Text to Image Synthesis Using Generative Adversarial Networks
• Data-Efficient Instance Generation from Instance Discrimination
• On the Evaluation of Conditional GANs
• A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
• TediGAN: Text-Guided Diverse Face Image Generation and Manipulation
• Autoregressive Quantile Networks for Generative Modeling
• Using latent space regression to analyze and leverage compositionality in GANs
• Language Guided Fashion Image Manipulation with Feature-wise Transformations
• Probabilistic Autoencoder
• Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting
• Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GAN
• GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
• PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network
• Generating Multiple Objects at Spatially Distinct Locations
• Attention2AngioGAN: Synthesizing Fluorescein Angiography from Retinal Fundus Images using Generative Adversarial Networks
• On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
• Learning to Defend by Learning to Attack
• Simple yet Effective Way for Improving the Performance of GAN
• Convolutional Generation of Textured 3D Meshes
• Landmark Assisted CycleGAN for Cartoon Face Generation
• Focal Frequency Loss for Image Reconstruction and Synthesis
• House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation
• FedGAN: Federated Generative Adversarial Networks for Distributed Data
• Adversarial score matching and improved sampling for image generation
• Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations
• Feature Quantization Improves GAN Training
• Physics-informed GANs for Coastal Flood Visualization
• Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data
• Counterfactuals uncover the modular structure of deep generative models
• Improved Contrastive Divergence Training of Energy Based Models
• Why Spectral Normalization Stabilizes GANs: Analysis and Improvements
• Sketch-Guided Scenery Image Outpainting
• Text as Neural Operator: Image Manipulation by Text Instruction
• Nonlinear 3D Cosmic Web Simulation with Heavy-Tailed Generative Adversarial Networks
• Sinkhorn AutoEncoders
• Fundus2Angio: A Conditional GAN Architecture for Generating Fluorescein Angiography Images from Retinal Fundus Photography
• Improved Consistency Regularization for GANs
• Image Amodal Completion: A Survey
• Deep Image Spatial Transformation for Person Image Generation
• An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning
• Complement Face Forensic Detection and Localization with FacialLandmarks
• Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation
• ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
• Towards Real-World Blind Face Restoration with Generative Facial Prior
• GANs May Have No Nash Equilibria
• GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint
• Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
• Hierarchical Quantized Autoencoders
• DeepFlow: History Matching in the Space of Deep Generative Models
• High-resolution Deep Convolutional Generative Adversarial Networks
• Decentralized Learning of Generative Adversarial Networks from Non-iid Data
• Cross-domain Correspondence Learning for Exemplar-based Image Translation
• X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
• The Shape of Data: Intrinsic Distance for Data Distributions
• Regularization Methods for Generative Adversarial Networks: An Overview of Recent Studies
• Cross-Domain Few-Shot Learning by Representation Fusion
• Improving Text-to-Image Synthesis Using Contrastive Learning
• Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model
• Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks
• Hierarchical Autoregressive Image Models with Auxiliary Decoders
• DP-Image: Differential Privacy for Image Data in Feature Space
• Neural Language Generation: Formulation, Methods, and Evaluation
• Cross Modal Compression: Towards Human-comprehensible Semantic Compression
• ShapeMOD: Macro Operation Discovery for 3D Shape Programs
• Evaluating Text GANs as Language Models
• Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
• Semi-supervised Image Attribute Editing using Generative Adversarial Networks
• Skill Rating for Generative Models
• Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
• StyleGAN2 Distillation for Feed-forward Image Manipulation
• FCC-GAN: A Fully Connected and Convolutional Net Architecture for GANs
• On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks
• Cali-Sketch: Stroke Calibration and Completion for High-Quality Face Image Generation from Human-Like Sketches
• GAN Prior Embedded Network for Blind Face Restoration in the Wild
• One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing
• Universal Rate-Distortion-Perception Representations for Lossy Compression
• How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models
• Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders
• Hybrid Discriminative-Generative Training via Contrastive Learning
• Improving the Fairness of Deep Generative Models without Retraining
• Towards Open-World Text-Guided Face Image Generation and Manipulation
• CloudCast: A Satellite-Based Dataset and Baseline for Forecasting Clouds
• Creative Sketch Generation
• Human Motion Transfer with 3D Constraints and Detail Enhancement
• Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images
• Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss
• Text-to-Face Generation with StyleGAN2
• Self-Supervised Variational Auto-Encoders
• Adversarial Learning for Improved Onsets and Frames Music Transcription
• High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks
• House-GAN++: Generative Adversarial Layout Refinement Networks
• Using Scene Graph Context to Improve Image Generation
• Review of end-to-end speech synthesis technology based on deep learning
• From Here to There: Video Inbetweening Using Direct 3D Convolutions
• Responsible Disclosure of Generative Models Using Scalable Fingerprinting
• InfinityGAN: Towards Infinite-Pixel Image Synthesis
• Adapting Object Detectors with Conditional Domain Normalization
• Fast and Provable ADMM for Learning with Generative Priors
• Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets
• VFlow: More Expressive Generative Flows with Variational Data Augmentation
• FairFaceGAN: Fairness-aware Facial Image-to-Image Translation
• Structural-analogy from a Single Image Pair
• Smoothness and Stability in GANs
• Encoding Invariances in Deep Generative Models
• A Spectral Energy Distance for Parallel Speech Synthesis
• Adversarial Lipschitz Regularization
• Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
• Text and Style Conditioned GAN for Generation of Offline Handwriting Lines
• Image-to-Image Translation: Methods and Applications
• Cascaded Refinement Network for Point Cloud Completion
• Exploring the Evolution of GANs through Quality Diversity
• Conservation AI: Live Stream Analysis for the Detection of Endangered Species Using Convolutional Neural Networks and Drone Technology
• Remote Sensing Image Translation via Style-Based Recalibration Module and Improved Style Discriminator
• PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention
• Gotta Go Fast When Generating Data with Score-Based Models
• COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network
• Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
• LaFIn: Generative Landmark Guided Face Inpainting
• Taming Visually Guided Sound Generation
• On the Latent Space of Wasserstein Auto-Encoders
• Towards Realistic 3D Embedding via View Alignment
• On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach
• Mimicry: Towards the Reproducibility of GAN Research
• Towards Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs
• Generative Latent Flow
• Wasserstein-2 Generative Networks
• 3DGAUnet: 3D generative adversarial networks with a 3D U-Net based generator to achieve the accurate and effective synthesis of clinical tumor image data for pancreatic cancer
• Enhancing Mechanical Metamodels with a Generative Model-Based Augmented Training Dataset
• Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction
• GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling
• A Relaxed Inertial Forward-Backward-Forward Algorithm for Solving Monotone Inclusions with Application to GANs
• Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation
• Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks
• Non Gaussian Denoising Diffusion Models
• IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning
• Performance of GAN-based augmentation for deep learning COVID-19 image classification
• Fréchet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms
• MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration
• Age-Oriented Face Synthesis with Conditional Discriminator Pool and Adversarial Triplet Loss
• On the distance between two neural networks and the stability of learning
• InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation
• Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
• 4D Facial Expression Diffusion Model
• A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
• Human Motion Prediction via Spatio-Temporal Inpainting
• An Internal Learning Approach to Video Inpainting
• Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
• Disentangled Recurrent Wasserstein Autoencoder
• Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning
• Negative Momentum for Improved Game Dynamics
• A Non-Parametric Test to Detect Data-Copying in Generative Models
• On the Effectiveness of Least Squares Generative Adversarial Networks
• Multi-StyleGAN: Towards Image-Based Simulation of Time-Lapse Live-Cell Microscopy
• When OT meets MoM: Robust estimation of Wasserstein Distance
• Gesture-to-Gesture Translation in the Wild via Category-Independent Conditional Maps
• Guided Image-to-Image Translation with Bi-Directional Feature Transformation
• Compressing PDF sets using generative adversarial networks
• Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology
• Fair Generative Modeling via Weak Supervision
• Ranking CGANs: Subjective Control over Semantic Image Attributes
• Emergence of Object Segmentation in Perturbed Generative Models
• Dual Contrastive Learning for Unsupervised Image-to-Image Translation
• Autoencoding Variational Autoencoder
• RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesis
• GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
• Variational Autoencoders with Normalizing Flow Decoders
• Generative Adversarial Networks (GANs): What it can generate and What it cannot?
• Learning Energy-Based Models by Diffusion Recovery Likelihood
• Real or Not Real, that is the Question
• Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks
• Diverse Image Inpainting with Bidirectional and Autoregressive Transformers
• Towards 3D Dance Motion Synthesis and Control
• Implicit competitive regularization in GANs
• Image Generation From Small Datasets via Batch Statistics Adaptation
• Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
• Deep Generative Models for Distribution-Preserving Lossy Compression
• This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Faces
• SRGAN: Training Dataset Matters
• The Six Fronts of the Generative Adversarial Networks
• Few-shot Image Generation via Cross-domain Correspondence
• Scaling Autoregressive Video Models
• Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks
• Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
• GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
• A Utility-Preserving GAN for Face Obscuration
• Accelerating Sparse Deep Neural Networks
• Progressive Semantic-Aware Style Transformation for Blind Face Restoration
• Semi-Supervised StyleGAN for Disentanglement Learning
• K-Hairstyle: A Large-scale Korean Hairstyle Dataset for Virtual Hair Editing and Hairstyle Classification
• Adversarial representation learning for private speech generation
• Perceptual Generative Autoencoders
• Bridging the gap between paired and unpaired medical image translation
• Procedural content generation of puzzle games using conditional generative adversarial networks
• MISS GAN: A Multi-IlluStrator Style Generative Adversarial Network for image to illustration translation
• Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks
• Improving the Speed and Quality of GAN by Adversarial Training
• Transformation-based Adversarial Video Prediction on Large-Scale Data
• Virtual Staining of Label-Free Tissue in Imaging Mass Spectrometry
• Example-Guided Style Consistent Image Synthesis from Semantic Labeling
• A likelihood approach to nonparametric estimation of a singular distribution using deep generative models
• Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation
• MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis
• Quantitatively Evaluating GANs With Divergences Proposed for Training
• Latent Translation: Crossing Modalities by Bridging Generative Models
• Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss
• SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains
• Explanation by Progressive Exaggeration
• Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder
• Generating unseen complex scenes: are we there yet?
• Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation
• Composite Score for Anomaly Detection in Imbalanced Real-World Industrial Dataset
• UGAN: Untraceable GAN for Multi-Domain Face Translation
• Video Generation from Single Semantic Label Map
• Understanding Overparameterization in Generative Adversarial Networks
• AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
• Unsupervised Medical Image Segmentation with Adversarial Networks: From Edge Diagrams to Segmentation Maps
• Style Transfer with Diffusion Models for Synthetic-to-Real Domain Adaptation
• Score-based Generative Modeling in Latent Space
• The Inductive Bias of Restricted f-GANs
• Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample
• FTGAN: A Fully-trained Generative Adversarial Networks for Text to Face Generation
• Adversarial Generation of Time-Frequency Features with application in audio synthesis
• SGD Learns One-Layer Networks in WGANs
• A Style-Aware Content Loss for Real-time HD Style Transfer
• DeepFaceEditing: Deep Face Generation and Editing with Disentangled Geometry and Appearance Control
• OPA: Object Placement Assessment Dataset
• Generating unrepresented proportions of geological facies using Generative Adversarial Networks
• Spectral Regularization for Combating Mode Collapse in GANs
• SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation
• Parallel Scheduled Sampling
• Image Morphing with Perceptual Constraints and STN Alignment
• Diverse Multimedia Layout Generation with Multi Choice Learning
• Large-scale multilingual audio visual dubbing
• PU-GAN: a Point Cloud Upsampling Adversarial Network
• Lipizzaner: A System That Scales Robust Generative Adversarial Network Training
• Competitive Training of Mixtures of Independent Deep Generative Models
• PISE: Person Image Synthesis and Editing with Decoupled GAN
• FaR-GAN for One-Shot Face Reenactment
• Globally Injective ReLU Networks
• Regularizing Generative Adversarial Networks under Limited Data
• Data Augmentation in Earth Observation: A Diffusion Model Approach
• Self-Adversarial Learning with Comparative Discrimination for Text Generation
• Densely connected normalizing flows
• Newton-type Methods for Minimax Optimization
• Generative Convolution Layer for Image Generation
• Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis
• Unsupervised Image-to-Image Translation via Pre-trained StyleGAN2 Network
• Jointly Measuring Diversity and Quality in Text Generation Models
• Feature Unlearning for Pre-trained GANs and VAEs
• Parser-Free Virtual Try-on via Distilling Appearance Flows
• Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation
• On the Units of GANs (Extended Abstract)
• Latent Space Factorisation and Manipulation via Matrix Subspace Projection
• Implicit Rank-Minimizing Autoencoder
• More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval
• Unbiased Auxiliary Classifier GANs with MINE
• CFA-Net: Controllable Face Anonymization Network with Identity Representation Manipulation
• Source Separation with Deep Generative Priors
• Deep Exemplar-based Video Colorization
• Investigating Under and Overfitting in Wasserstein Generative Adversarial Networks
• Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark
• A Brief Introduction to Generative Models
• Realistic Ultrasound Image Synthesis for Improved Classification of Liver Disease
• Evaluation in Neural Style Transfer: A Review
• Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes
• Image Obfuscation for Privacy-Preserving Machine Learning
• Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
• PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain
• Human Motion Transfer from Poses in the Wild
• Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE
• Joint Generative and Contrastive Learning for Unsupervised Person Re-identification
• Guided Variational Autoencoder for Disentanglement Learning
• Adversarial Learned Molecular Graph Inference and Generation
• Learning disconnected manifolds: a no GANs land
• Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
• The Spatially-Correlative Loss for Various Image Translation Tasks
• IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition
• Isometric Autoencoders
• MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translation
• PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering
• Alleviating Mode Collapse in GAN via Diversity Penalty Module
• Cascade EF-GAN: Progressive Facial Expression Editing with Local Focuses
• Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN
• COCO-GAN: Generation by Parts via Conditional Coordinating
• Training Generative Adversarial Networks Via Turing Test
• PolyGAN: High-Order Polynomial Generators
• Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion
• GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks
• Stable Opponent Shaping in Differentiable Games
• TM-NET: Deep Generative Networks for Textured Meshes
• MulGAN: Facial Attribute Editing by Exemplar
• Face-to-Parameter Translation for Game Character Auto-Creation
• Controllable and Progressive Image Extrapolation
• Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving
• How does Lipschitz Regularization Influence GAN Training?
• DwNet: Dense warp-based network for pose-guided human video generation
• LaMD: Latent Motion Diffusion for Image-Conditional Video Generation
• Towards Efficient and Unbiased Implementation of Lipschitz Continuity in GANs
• Effective Universal Unrestricted Adversarial Attacks using a MOE Approach
• FIRe-GAN: A novel Deep Learning-based infrared-visible fusion method for wildfire imagery
• Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
• AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks
• DG-Font: Deformable Generative Networks for Unsupervised Font Generation
• DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning
• An Improved Self-supervised GAN via Adversarial Training
• Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks
• A Survey and Taxonomy of Adversarial Neural Networks for Text-to-Image Synthesis
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator
• Quantitative analysis of robot gesticulation behavior
• A Contrastive Learning Approach for Training Variational Autoencoder Priors
• Generative Adversarial U-Net for Domain-free Medical Image Augmentation
• Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks
• Fast Mixing of Multi-Scale Langevin Dynamics under the Manifold Hypothesis
• PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images
• High Fidelity Face Manipulation with Extreme Poses and Expressions
• Image-to-image Translation via Hierarchical Style Disentanglement
• Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models
• Metropolis-Hastings view on variational inference and adversarial training
• Mask-Guided Portrait Editing with Conditional GANs
• GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation
• Deep Direct Volume Rendering: Learning Visual Feature Mappings From Exemplary Images
• Balancing Reconstruction Quality and Regularisation in ELBO for VAEs
• Audio-Driven Emotional Video Portraits
• Distributional Sliced-Wasserstein and Applications to Generative Modeling
• Regularized Autoencoders via Relaxed Injective Probability Flow
• Generating Images with Sparse Representations
• (q,p)-Wasserstein GANs: Comparing Ground Metrics for Wasserstein GANs
• Triple Generative Adversarial Networks
• Editing in Style: Uncovering the Local Semantics of GANs
• Neural Design Network: Graphic Layout Generation with Constraints
• Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs
• The Devil is in the Decoder: Classification, Regression and GANs
• EncryptGAN: Image Steganography with Domain Transform
• Symbolic Music Generation with Diffusion Models
• Enhancing the Performance of Practical Profiling Side-Channel Attacks Using Conditional Generative Adversarial Networks
• Adaptive Model Learning of Neural Networks with UUB Stability for Robot Dynamic Estimation
• Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models
• Conditional Image Generation with Score-Based Diffusion Models
• Human Image Generation: A Comprehensive Survey
• Semantics-Aware Image to Image Translation and Domain Transfer
• Adversarial Image Composition with Auxiliary Illumination
• Generating Text Sequence Images for Recognition
• Group Equivariant Generative Adversarial Networks
• Relightable 3D Head Portraits from a Smartphone Video
• Image Inpainting Guided by Coherence Priors of Semantics and Textures
• Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms
• Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors
• One-Shot Identity-Preserving Portrait Reenactment
• Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation
• KoDF: A Large-scale Korean DeepFake Detection Dataset
• In-Domain GAN Inversion for Real Image Editing
• Training GANs with Stronger Augmentations via Contrastive Discriminator
• ZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translation
• Positional Normalization
• FICGAN: Facial Identity Controllable GAN for De-identification
• Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation
• Dual Variational Generation for Low-Shot Heterogeneous Face Recognition
• Training Generative Reversible Networks
• Neural Architecture Search for Deep Image Prior
• WaveFill: A Wavelet-based Generation Network for Image Inpainting
• RPGAN: GANs Interpretability via Random Routing
• Conditional GANs with Auxiliary Discriminative Classifier
• Compound Frechet Inception Distance for Quality Assessment of GAN Created Images
• MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
• Semantic Bottleneck Scene Generation
• Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference
• FLNet: Landmark Driven Fetching and Learning Network for Faithful Talking Facial Animation Synthesis
• A mean-field analysis of two-player zero-sum games
• Learning latent representations across multiple data domains using Lifelong VAEGAN
• A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis
• Few-shot Video-to-Video Synthesis
• Understanding the Effectiveness of Lipschitz-Continuity in Generative Adversarial Nets
• COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder
• Anycost GANs for Interactive Image Synthesis and Editing
• HyperInverter: Improving StyleGAN Inversion via Hypernetwork
• One-Shot Generative Domain Adaptation
• Dynamics of Fourier Modes in Torus Generative Adversarial Networks
• GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation
• Stylized Face Sketch Extraction via Generative Prior with Limited Data
• PROUD: PaRetO-gUided Diffusion Model for Multi-objective Generation
• Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach
• GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework
• Palm-GAN: Generating Realistic Palmprint Images Using Total-Variation Regularized GAN
• No MCMC for me: Amortized sampling for fast and stable training of energy-based models
• Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation
• Instance-level Facial Attributes Transfer with Geometry-Aware Flow
• Privacy-preserving medical image analysis
• Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
• MineGAN: effective knowledge transfer from GANs to target domains with few images
• NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency
• Toward Accurate and Realistic Virtual Try-on Through Shape Matching and Multiple Warps
• Recapture as You Want
• Additional Look into GAN-based Augmentation for Deep Learning COVID-19 Image Classification
• Data Separability for Neural Network Classifiers and the Development of a Separability Index
• Deep Line Art Video Colorization with a Few References
• Object-Centric Image Generation with Factored Depths, Locations, and Appearances
• TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting
• AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation
• Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data
• RankGAN: A Maximum Margin Ranking GAN for Generating Faces
• Leveraging Visual Question Answering to Improve Text-to-Image Synthesis
• VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
• Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
• Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach
• Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective
• Neural Architecture Search for Generative Adversarial Networks: A Comprehensive Review and Critical Analysis
• Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation
• Teachers Do More Than Teach: Compressing Image-to-Image Models
• Reciprocal Translation between SAR and Optical Remote Sensing Images with Cascaded-Residual Adversarial Networks
• Generative Minimization Networks: Training GANs Without Competition
• Phase Retrieval with Holography and Untrained Priors: Tackling the Challenges of Low-Photon Nanoscale Imaging
• $(f,\Gamma )$-Divergences: Interpolating between $f$-Divergences and Integral Probability Metrics
• Label-Noise Robust Generative Adversarial Networks
• PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
• Image Generation from Layout
• Trusted Artificial Intelligence: Towards Certification of Machine Learning Applications
• On Data Augmentation and Adversarial Risk: An Empirical Analysis
• Positional Encoding as Spatial Inductive Bias in GANs
• A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems
• Super-resolution Variational Auto-Encoders
• Self-Supervised GANs via Auxiliary Rotation Loss
• Language-Driven Image Style Transfer
• Styleformer: Transformer based Generative Adversarial Networks with Style Vector
• Self-Supervised GANs with Label Augmentation
• Spectral-GANs for High-Resolution 3D Point-cloud Generation
• Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation
• Image Synthesis From Reconfigurable Layout and Style
• Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
• Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation
• Anytime Sampling for Autoregressive Models via Ordered Autoencoding
• FReeNet: Multi-Identity Face Reenactment
• Single Underwater Image Restoration by Contrastive Learning
• SceneGen: Learning to Generate Realistic Traffic Scenes
• SketchyCOCO: Image Generation from Freehand Scene Sketches
• Self-labeled Conditional GANs
• Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders
• GAN-based Generation and Automatic Selection of Explanations for Neural Networks
• cGANs with Conditional Convolution Layer
• Learning to Take Directions One Step at a Time
• Denoising Diffusion Gamma Models
• MR-GAN: Manifold Regularized Generative Adversarial Networks
• Hair-GANs: Recovering 3D Hair Structure from a Single Image
• Make a Face: Towards Arbitrary High Fidelity Face Manipulation
• Conditional Adversarial Generative Flow for Controllable Image Synthesis
• Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter
• Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?
• TSIT: A Simple and Versatile Framework for Image-to-Image Translation
• Rethinking Image Deraining via Rain Streaks and Vapors
• Reviewing FID and SID Metrics on Generative Adversarial Networks
• Progressive Limb-Aware Virtual Try-On
• A Survey of Spatio-Temporal EEG data Analysis: from Models to Applications
• GANs beyond divergence minimization
• Privacy Leakage of SIFT Features via Deep Generative Model based Image Reconstruction
• Causal Adversarial Network for Learning Conditional and Interventional Distributions
• Tdcgan: Temporal Dilated Convolutional Generative Adversarial Network for End-to-end Speech Enhancement
• MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network
• Neural Turtle Graphics for Modeling City Road Layouts
• Optimality and Stability in Non-Convex Smooth Games
• Using Mode Connectivity for Loss Landscape Analysis
• Chunked Autoregressive GAN for Conditional Waveform Synthesis
• Robust Pose Transfer with Dynamic Details using Neural Video Rendering
• Particle Cloud Generation with Message Passing Generative Adversarial Networks
• Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
• Unpaired Image Super-Resolution using Pseudo-Supervision
• Constrained Generative Adversarial Network Ensembles for Sharable Synthetic Data Generation
• Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
• CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network
• SocialInteractionGAN: Multi-person Interaction Sequence Generation
• Style-based Point Generator with Adversarial Rendering for Point Cloud Completion
• Decentralized Attribution of Generative Models
• Trumpets: Injective Flows for Inference and Inverse Problems
• Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization
• Capturing Label Characteristics in VAEs
• Normalizing Flows Across Dimensions
• Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses
• Train simultaneously, generalize better: Stability of gradient-based minimax learners
• Adversarially Approximated Autoencoder for Image Generation and Manipulation
• Information-Theoretic Visual Explanation for Black-Box Classifiers
• DeepBlur: A Simple and Effective Method for Natural Image Obfuscation
• Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Network
• A survey on Variational Autoencoders from a GreenAI perspective
• Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent
• Mask Based Unsupervised Content Transfer
• Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images
• Conditional Image Generation and Manipulation for User-Specified Content
• Quality Evaluation of GANs Using Cross Local Intrinsic Dimensionality
• PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs
• Continuous Conditional Generative Adversarial Networks (cGAN) with Generator Regularization
• Conditional WGANs with Adaptive Gradient Balancing for Sparse MRI Reconstruction
• Dual Contrastive Loss and Attention for GANs
• Diffusion-Weighted Magnetic Resonance Brain Images Generation with Generative Adversarial Networks and Variational Autoencoders: A Comparison Study
• Attentive Normalization for Conditional Image Generation
• High Resolution Face Editing with Masked GAN Latent Code Optimization
• Using Simulated Data to Generate Images of Climate Change
• Coconditional Autoencoding Adversarial Networks for Chinese Font Feature Learning
• MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network
• Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
• Dual Adversarial Inference for Text-to-Image Synthesis
• A Survey of Deep Facial Attribute Analysis
• Unsupervised Change Detection in Satellite Images with Generative Adversarial Network
• Learning Multi-Site Harmonization of Magnetic Resonance Images Without Traveling Human Phantoms
• ComicGAN: Text-to-Comic Generative Adversarial Network
• Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives
• Generated Loss and Augmented Training of MNIST VAE
• Simple Video Generation using Neural ODEs
• BachGAN: High-Resolution Image Synthesis from Salient Object Layout
• FaceController: Controllable Attribute Editing for Face in the Wild
• Generative Modeling with Optimal Transport Maps
• Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination
• CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
• Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning
• Measuring the Biases and Effectiveness of Content-Style Disentanglement
• First Order Generative Adversarial Networks
• Reference-guided Face Component Editing
• Hybrid Generative-Contrastive Representation Learning
• Data-efficient visuomotor policy training using reinforcement learning and generative models
• BézierSketch: A generative model for scalable vector sketches
• Memory-efficient Learning for High-Dimensional MRI Reconstruction
• GANs Can Play Lottery Tickets Too
• Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesis
• CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Network
• Can GAN originate new electronic dance music genres? -- Generating novel rhythm patterns using GAN with Genre Ambiguity Loss
• Deep Learning-based Face Super-Resolution: A Survey
• StyleUV: Diverse and High-fidelity UV Map Generative Model
• Learning to Transfer: Unsupervised Meta Domain Translation
• MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation
• Asymmetric GANs for Image-to-Image Translation
• Learning compositional functions via multiplicative weight updates
• Bi-level Feature Alignment for Versatile Image Translation and Manipulation
• Learning by Turning: Neural Architecture Aware Optimisation
• Diverse Semantic Image Synthesis via Probability Distribution Modeling
• On Characterizing GAN Convergence Through Proximal Duality Gap
• Using GANs to Synthesise Minimum Training Data for Deepfake Generation
• Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis
• Shape-Guided Clothing Warping for Virtual Try-On
• Synthetic-Neuroscore: Using A Neuro-AI Interface for Evaluating Generative Adversarial Networks
• Designing GANs: A Likelihood Ratio Approach
• Wasserstein-Wasserstein Auto-Encoders
• Task-agnostic Temporally Consistent Facial Video Editing
• GAN Cocktail: mixing GANs without dataset access
• Learning Neurosymbolic Generative Models via Program Synthesis
• CoNeS: Conditional neural fields with shift modulation for multi-sequence MRI translation
• Temporally coherent video anonymization through GAN inpainting
• xAI-GAN: Enhancing Generative Adversarial Networks via Explainable AI Systems
• An Acceleration Framework for High Resolution Image Synthesis
• Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
• FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition
• Importance Weighted Adversarial Variational Autoencoders for Spike Inference from Calcium Imaging Data
• IMAGINE: Image Synthesis by Image-Guided Model Inversion
• PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning
• GIQA: Generated Image Quality Assessment
• PowerGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks
• FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
• Improving Molecular Design by Stochastic Iterative Target Augmentation
• Talking-head Generation with Rhythmic Head Motion
• Nonconvex-Nonconcave Min-Max Optimization with a Small Maximization Domain
• Learning Prototype-oriented Set Representations for Meta-Learning
• Flow Contrastive Estimation of Energy-Based Models
• RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval
• A Game-Theoretic Approach to Multi-Agent Trust Region Optimization
• Unpaired Image-to-Image Translation using Adversarial Consistency Loss
• Improving Mini-batch Optimal Transport via Partial Transportation
• Approximating Human Judgment of Generated Image Quality
• JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting
• Generative Ratio Matching Networks
• Kernel Stein Generative Modeling
• Selective Synthetic Augmentation with Quality Assurance
• Manifold Topology Divergence: a Framework for Comparing Data Manifolds
• Learning Semantic Person Image Generation by Region-Adaptive Normalization
• Variational Conditional GAN for Fine-grained Controllable Image Generation
• Generalized Energy Based Models
• Automating Generative Deep Learning for Artistic Purposes: Challenges and Opportunities
• MatchingGAN: Matching-based Few-shot Image Generation
• 3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images
• Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections
• Unsupervised Eyeglasses Removal in the Wild
• Deep Generative Learning via Schrödinger Bridge
• Learning to Incorporate Structure Knowledge for Image Inpainting
• DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
• Learning Implicit Generative Models with Theoretical Guarantees
• Segmentation of Surgical Instruments for Minimally-Invasive Robot-Assisted Procedures Using Generative Deep Neural Networks
• Deep Generation of Face Images from Sketches
• Universal Face Restoration With Memorized Modulation
• NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
• Score-Guided Generative Adversarial Networks
• Bridging Global Context Interactions for High-Fidelity Image Completion
• CPOT: Channel Pruning via Optimal Transport
• Attribute2Font: Creating Fonts You Want From Attributes
• On Quantitative Evaluations of Counterfactuals
• MOGAN: Morphologic-structure-aware Generative Learning from a Single Image
• Generating Correct Answers for Progressive Matrices Intelligence Tests
• Deep Generative Learning via Variational Gradient Flow
• The Art of Food: Meal Image Synthesis from Ingredients
• Defending Medical Image Diagnostics against Privacy Attacks using Generative Methods
• MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
• Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
• On Transportation of Mini-batches: A Hierarchical Approach
• I Want This Product but Different : Multimodal Retrieval with Synthetic Query Expansion
• Influence Estimation for Generative Adversarial Networks
• Taming GANs with Lookahead-Minmax
• Augmented Sliced Wasserstein Distances
• GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving
• MosAIc: Finding Artistic Connections across Culture with Conditional Image Retrieval
• Unsupervised object-centric video generation and decomposition in 3D
• Generative Hierarchical Features from Synthesizing Images
• Example-Guided Image Synthesis across Arbitrary Scenes using Masked Spatial-Channel Attention and Self-Supervision
• Semantically Multi-modal Image Synthesis
• In&Out : Diverse Image Outpainting via GAN Inversion
• To Relieve Your Headache of Training an MRF, Take AdVIL
• Self-Supervised GAN Compression
• GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing
• DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network
• Model Extraction and Defenses on Generative Adversarial Networks
• Generative View Synthesis: From Single-view Semantics to Novel-view Images
• Practical and Consistent Estimation of f-Divergences
• Fast Universal Style Transfer for Artistic and Photorealistic Rendering
• Unsupervised multi-modal Styled Content Generation
• Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild
• Dual Attention GANs for Semantic Image Synthesis
• NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
• Bayesian modeling of insurance claims for hail damage
• A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization
• Disentangling representations of retinal images with generative models
• Direct May Not Be the Best: An Incremental Evolution View of Pose Generation
• DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
• TarGAN: Target-Aware Generative Adversarial Networks for Multi-modality Medical Image Translation
• Inclusive GAN: Improving Data and Minority Coverage in Generative Models
• Bayesian Reasoning with Trained Neural Networks
• In-N-Out: Towards Good Initialization for Inpainting and Outpainting
• Multimodal Image-to-Image Translation via Mutual Information Estimation and Maximization
• CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
• Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's Decision
• Training Generative Adversarial Networks in One Stage
• Image-to-Image Translation with Low Resolution Conditioning
• Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions
• Learning to simulate complex scenes
• StyleNAS: An Empirical Study of Neural Architecture Search to Uncover Surprisingly Fast End-to-End Universal Style Transfer Networks
• PriorGAN: Real Data Prior for Generative Adversarial Nets
• ReGO: Reference-Guided Outpainting for Scenery Image
• Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flow
• Domain-Specific Mappings for Generative Adversarial Style Transfer
• Toward Joint Image Generation and Compression using Generative Adversarial Networks
• Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions
• Image-to-Image Translation with Multi-Path Consistency Regularization
• Video Reenactment as Inductive Bias for Content-Motion Disentanglement
• Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions
• Online Exemplar Fine-Tuning for Image-to-Image Translation
• Dual Contradistinctive Generative Autoencoder
• Federated CycleGAN for Privacy-Preserving Image-to-Image Translation
• Spurious samples in deep generative models: bug or feature?
• Improving Style-Content Disentanglement in Image-to-Image Translation
• Bi-level Score Matching for Learning Energy-based Latent Variable Models
• SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans
• Assessing Dialogue Systems with Distribution Distances
• Human Pose Transfer with Augmented Disentangled Feature Consistency
• Example-Guided Scene Image Synthesis using Masked Spatial-Channel Attention and Patch-Based Self-Supervision
• Flow Guided Transformable Bottleneck Networks for Motion Retargeting
• MIASSR: An Approach for Medical Image Arbitrary Scale Super-Resolution
• Modeling EEG data distribution with a Wasserstein Generative Adversarial Network to predict RSVP Events
• GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)
• Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation
• SDE approximations of GANs training and its long-run behavior
• F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
• Bringing Old Photos Back to Life
• Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets
• Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification
• Efficient Learning of Generative Models via Finite-Difference Score Matching
• Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation
• GAN Memory with No Forgetting
• World-Consistent Video-to-Video Synthesis
• MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs
• UVA: A Universal Variational Framework for Continuous Age Analysis
• Sketch-to-Art: Synthesizing Stylized Art Images From Sketches
• Refining Deep Generative Models via Discriminator Gradient Flow
• CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling
• Unpaired Image-to-Image Translation via Latent Energy Transport
• Adaptive Weighted Discriminator for Training Generative Adversarial Networks
• Learning Disentangled Representations with Latent Variation Predictability
• Deep Fusion Network for Image Completion
• Cycle-Consistent Inverse GAN for Text-to-Image Synthesis
• To learn image super-resolution, use a GAN to learn how to do image degradation first
• Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification
• PD-GAN: Probabilistic Diverse GAN for Image Inpainting
• DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation
• Future Urban Scenes Generation Through Vehicles Synthesis
• Learning Neural Light Transport
• Contrastive Unpaired Translation using Focal Loss for Patch Classification
• Global and Local Alignment Networks for Unpaired Image-to-Image Translation
• Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy
• Extragradient with player sampling for faster Nash equilibrium finding
• Hyperbolic Generative Adversarial Network
• SDA-GAN: Unsupervised Image Translation Using Spectral Domain Attention-Guided Generative Adversarial Network
• On Computation and Generalization of GANs with Spectrum Control
• Latent Dirichlet Allocation in Generative Adversarial Networks
• Dreaming of Electrical Waves: Generative Modeling of Cardiac Excitation Waves using Diffusion Models
• M2GAN: A Multi-Stage Self-Attention Network for Image Rain Removal on Autonomous Vehicles
• Learning Global and Local Features of Normal Brain Anatomy for Unsupervised Abnormality Detection
• Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space
• DPD-InfoGAN: Differentially Private Distributed InfoGAN
• GAN Inversion for Out-of-Range Images with Geometric Transformations
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
• Boosting Image Outpainting with Semantic Layout Prediction
• Batch norm with entropic regularization turns deterministic autoencoders into generative models
• Entropy-regularized Optimal Transport Generative Models
• Adversarial Pixel-Level Generation of Semantic Images
• Semi-supervised Learning for Few-shot Image-to-Image Translation
• Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators
• Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)
• High-Resolution Complex Scene Synthesis with Transformers
• A Cyclically-Trained Adversarial Network for Invariant Representation Learning
• VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks
• Principled Interpolation in Normalizing Flows
• SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning
• Evaluating Generative Adversarial Networks on Explicitly Parameterized Distributions
• Stochastic Conditional Generative Networks with Basis Decomposition
• Reciprocal Adversarial Learning via Characteristic Functions
• Adversarial Framework for Unsupervised Learning of Motion Dynamics in Videos
• Cloud2Curve: Generation and Vectorization of Parametric Sketches
• BalaGAN: Image Translation Between Imbalanced Domains via Cross-Modal Transfer
• Interactive Label Cleaning with Example-based Explanations
• Robustness and Diversity Seeking Data-Free Knowledge Distillation
• Improved Transformer for High-Resolution GANs
• Very Long Natural Scenery Image Prediction by Outpainting
• Text-to-Image Generation Grounded by Fine-Grained User Attention
• FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
• Conditional Denoising of Remote Sensing Imagery Using Cycle-Consistent Deep Generative Models
• Controllable Orthogonalization in Training DNNs
• Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
• Optimal Transport Relaxations with Application to Wasserstein GANs
• BreGMN: scaled-Bregman Generative Modeling Networks
• Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
• Deconstructing Generative Adversarial Networks
• Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
• Improving the Evaluation of Generative Models with Fuzzy Logic
• Spherical Image Generation from a Single Normal Field of View Image by Considering Scene Symmetry
• Orthogonal Wasserstein GANs
• Unsupervised Multi-Domain Multimodal Image-to-Image Translation with Explicit Domain-Constrained Disentanglement
• Searching for an (un)stable equilibrium: experiments in training generative models without data
• Exploring Generative Physics Models with Scientific Priors in Inertial Confinement Fusion
• "Best-of-Many-Samples" Distribution Matching
• Sample weighting as an explanation for mode collapse in generative adversarial networks
• TinyGAN: Distilling BigGAN for Conditional Image Generation
• Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild
• Controllable Image Synthesis via SegVAE
• Client Adaptation improves Federated Learning with Simulated Non-IID Clients
• Few-shot Compositional Font Generation with Dual Memory
• Generative Adversarial Data Programming
• Intuitive, Interactive Beard and Hair Synthesis with Generative Models
• Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning
• Semantic Image Manipulation Using Scene Graphs
• A Neuro-AI Interface for Evaluating Generative Adversarial Networks
• Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics
• Everything's Talkin': Pareidolia Face Reenactment
• Content-Aware GAN Compression
• Human De-occlusion: Invisible Perception and Recovery for Humans
• Restore from Restored: Single-image Inpainting
• Deep Consensus Learning
• Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation
• Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack
• A Generative Model for Hallucinating Diverse Versions of Super Resolution Images
• Generative Learning With Euler Particle Transport
• GMM-Based Generative Adversarial Encoder Learning
• Slimmable Generative Adversarial Networks
• DECOR-GAN: 3D Shape Detailization by Conditional Refinement
• Generating Unobserved Alternatives
• Diffusion models for Handwriting Generation
• Omni-GAN: On the Secrets of cGANs and Beyond
• Vehicle Reconstruction and Texture Estimation Using Deep Implicit Semantic Template Mapping
• PC-GAIN: Pseudo-label Conditional Generative Adversarial Imputation Networks for Incomplete Data
• Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis
• Structure-aware Image Inpainting with Two Parallel Streams
• Manifold-preserved GANs
• Inferential Wasserstein Generative Adversarial Networks
• Multilevel Knowledge Transfer for Cross-Domain Object Detection
• Artificial Intelligence Hybrid Deep Learning Model for Groundwater Level Prediction Using MLP-ADAM
• InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihood
• Independent Encoder for Deep Hierarchical Unsupervised Image-to-Image Translation
• Rectangular Flows for Manifold Learning
• BaMBNet: A Blur-aware Multi-branch Network for Defocus Deblurring
• Transfer Learning with Pre-trained Conditional Generative Models
• Expressive Communication: A Common Framework for Evaluating Developments in Generative Models and Steering Interfaces
• SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches
• Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
• On Predicting Generalization using GANs
• DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing
• Harnessing Optoelectronic Noises in a Photonic Generative Network
• Differential-Critic GAN: Generating What You Want by a Cue of Preferences
• Double Descent and Other Interpolation Phenomena in GANs
• Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows
• CDMA: A Practical Cross-Device Federated Learning Algorithm for General Minimax Problems
• Continuous Face Aging via Self-estimated Residual Age Embedding
• Exploring The Effect of High-frequency Components in GANs Training
• DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
• Latent Neural Differential Equations for Video Generation
• not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution
• Autoregressive Score Matching
• Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
• SMYRF: Efficient Attention using Asymmetric Clustering
• A deep learning based interactive sketching system for fashion images design
• Integrating Categorical Semantics into Unsupervised Domain Translation
• Learning Manifold Implicitly via Explicit Heat-Kernel Learning
• SAFRON: Stitching Across the Frontier for Generating Colorectal Cancer Histology Images
• Accelerated WGAN update strategy with loss change rate balancing
• Lessons Learned from the Training of GANs on Artificial Datasets
• Instance Selection for GANs
• Go with the Flow: Adaptive Control for Neural ODEs
• InfoScrub: Towards Attribute Privacy by Targeted Obfuscation
• Synthesis and Edition of Ultrasound Images via Sketch Guided Progressive Growing GANs
• Perceptual Image Super-Resolution with Progressive Adversarial Network
• Blur, Noise, and Compression Robust Generative Adversarial Networks
• Pores for thought: The use of generative adversarial networks for the stochastic reconstruction of 3D multi-phase electrode microstructures with periodic boundaries
• A Novel Framework for Selection of GANs for an Application
• Adversarial Monte Carlo Meta-Learning of Optimal Prediction Procedures
• Alleviation of Gradient Exploding in GANs: Fake Can Be Real
• Double cycle-consistent generative adversarial network for unsupervised conditional generation
• Radon Sobolev Variational Auto-Encoders
• A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings
• Gradient penalty from a maximum margin perspective
• An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation
• Attribute-Driven Spontaneous Motion in Unpaired Image Translation
• Stable Rank Normalization for Improved Generalization in Neural Networks and GANs
• Fashion Editing with Adversarial Parsing Learning
• Hierarchy Composition GAN for High-fidelity Image Synthesis
• Precision-Recall Curves Using Information Divergence Frontiers
• A Forest from the Trees: Generation through Neighborhoods
• Collaborative Sampling in Generative Adversarial Networks
• Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling
• Pairwise Augmented GANs with Adversarial Reconstruction Loss
• How good is my GAN?
• Lipschitz Constrained GANs via Boundedness and Continuity
• Fréchet ChemNet Distance: A metric for generative models for molecules in drug discovery
• Tempered Adversarial Networks
• WAS-VTON: Warping Architecture Search for Virtual Try-on Network
• Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization
• Generative Transition Mechanism to Image-to-Image Translation via Encoded Transformation
• Combining Attention with Flow for Person Image Synthesis
• IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse
• Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection
• Deep learning-based bias transfer for overcoming laboratory differences of microscopic images
• A Survey on GAN Acceleration Using Memory Compression Technique
• Unsupervised Disentanglement of Linear-Encoded Facial Semantics
• Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning
• On the Exploitation of Neuroevolutionary Information: Analyzing the Past for a More Efficient Future
• F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain
• A 3D model-based approach for fitting masks to faces in the wild
• NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Dataset and Study
• Realistic Image Synthesis with Configurable 3D Scene Layouts
• Exploiting Style and Attention in Real-World Super-Resolution
• MaskAAE: Latent space optimization for Adversarial Auto-Encoders
• Hard-Aware Fashion Attribute Classification
• The Image Local Autoregressive Transformer
• G3AN: Disentangling Appearance and Motion for Video Generation
• Normalizing Flows with Multi-Scale Autoregressive Priors
• Adversarial sampling of unknown and high-dimensional conditional distributions
• S2IGAN: Speech-to-Image Generation via Adversarial Learning
• Generating Memorable Images Based on Human Visual Memory Schemas
• Variance Constrained Autoencoding
• Noise Homogenization via Multi-Channel Wavelet Filtering for High-Fidelity Sample Generation in GANs
• Learning Signal-Agnostic Manifolds of Neural Fields
• Making Method of Moments Great Again? -- How can GANs learn distributions
• To Regularize or Not To Regularize? The Bias Variance Trade-off in Regularized AEs
• Image Synthesis via Semantic Composition
• Exploiting the Hidden Tasks of GANs: Making Implicit Subproblems Explicit
• Semantically Robust Unpaired Image Translation for Data with Unmatched Semantics Statistics
• An Empirical Study of Generative Models with Encoders
• Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion
• Synthesizing 3D Shapes from Silhouette Image Collections using Multi-projection Generative Adversarial Networks
• Multi-Density Sketch-to-Image Translation Network
• LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders
• Unsupervised Many-to-Many Image-to-Image Translation Across Multiple Domains
• De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks
• Distributional Discrepancy: A Metric for Unconditional Text Generation
• Toward Accurate and Realistic Outfits Visualization with Attention to Details
• D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
• Words as Art Materials: Generating Paintings with Sequential GANs
• Modeling Artistic Workflows for Image Generation and Editing
• Learning End-to-End Action Interaction by Paired-Embedding Data Augmentation
• Benefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization
• Evolutionary Generative Adversarial Networks with Crossover Based Knowledge Distillation
• Conditional Frechet Inception Distance
• LEED: Label-Free Expression Editing via Disentanglement
• Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder
• Low-Rank Subspaces in GANs
• Amortised Learning by Wake-Sleep
• Interpreting Spatially Infinite Generative Models
• Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions
• Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
• Symmetric Wasserstein Autoencoders
• Weakly-supervised Generative Adversarial Networks for medical image classification
• DeepGIN: Deep Generative Inpainting Network for Extreme Image Inpainting
• DeepLandscape: Adversarial Modeling of Landscape Video
• Decoupling Global and Local Representations via Invertible Generative Flows
• A Layer-Based Sequential Framework for Scene Generation with GANs
• Channel-Directed Gradients for Optimization of Convolutional Neural Networks
• Person-in-Context Synthesiswith Compositional Structural Space
• LaDDer: Latent Data Distribution Modelling with a Generative Prior
• Neural Crossbreed: Neural Based Image Metamorphosis
• Pairwise-GAN: Pose-based View Synthesis through Pair-Wise Training
• Improving Text to Image Generation using Mode-seeking Function
• Disentangling the Spatial Structure and Style in Conditional VAE
• Generative Model without Prior Distribution Matching
• DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis
• A Novel Measure to Evaluate Generative Adversarial Networks Based on Direct Analysis of Generated Images
• CariMe: Unpaired Caricature Generation with Multiple Exaggerations
• Momentum Centering and Asynchronous Update for Adaptive Gradient Methods
• Shapes and Context: In-the-Wild Image Synthesis & Manipulation
• Lifting 2D StyleGAN for 3D-Aware Face Generation
• Deep Image Synthesis from Intuitive User Input: A Review and Perspectives
• On the Anomalous Generalization of GANs
• Encoder-Powered Generative Adversarial Networks
• A Generative Approach Towards Improved Robotic Detection of Marine Litter
• Autoencoding Under Normalization Constraints
• Informative Sample Mining Network for Multi-Domain Image-to-Image Translation
• Painting Outside as Inside: Edge Guided Image Outpainting via Bidirectional Rearrangement with Progressive Step Learning
• Optimal Transport Based Generative Autoencoders
• Fine-grained Image-to-Image Transformation towards Visual Recognition
• One-Shot Image-to-Image Translation via Part-Global Learning with a Multi-adversarial Framework
• Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis
• On The Distribution of Penultimate Activations of Classification Networks
• Kernel Mean Matching for Content Addressability of GANs
• Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons
• TCAM-Diff: Triplane-Aware Cross-Attention Medical Diffusion Model
• A Framework and Dataset for Abstract Art Generation via CalligraphyGAN
• Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection
• Detecting GAN generated errors
• Attributes Aware Face Generation with Generative Adversarial Networks
• Unsupervised Adversarial Image Inpainting
• Characteristic Regularisation for Super-Resolving Face Images
• Prb-GAN: A Probabilistic Framework for GAN Modelling
• Face Attribute Invertion
• AE-OT-GAN: Training GANs from data specific latent distribution
• Less Memory, Faster Speed: Refining Self-Attention Module for Image Reconstruction
• Latent Behavior Diffusion for Sequential Reaction Generation in Dyadic Setting
• An Assessment of GANs for Identity-related Applications
• Self-Supervised Sketch-to-Image Synthesis
• CookGAN: Meal Image Synthesis from Ingredients
• Towards a Neural Graphics Pipeline for Controllable Image Generation
• Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
• Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows
• From Rain Generation to Rain Removal
• HRVGAN: High Resolution Video Generation using Spatio-Temporal GAN
• Discriminative Multi-level Reconstruction under Compact Latent Space for One-Class Novelty Detection
• Correspondence Learning for Controllable Person Image Generation
• A New Distributed Method for Training Generative Adversarial Networks
• TreeGAN: Incorporating Class Hierarchy into Image Generation
• Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
• L-Verse: Bidirectional Generation Between Image and Text
• SeCGAN: Parallel Conditional Generative Adversarial Networks for Face Editing via Semantic Consistency
• Discriminative Cross-Modal Data Augmentation for Medical Imaging Applications
• GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks
• Unrealistic Feature Suppression for Generative Adversarial Networks
• Sampling Using Neural Networks for colorizing the grayscale images
• Conditioning Trick for Training Stable GANs
• Implicit Subspace Prior Learning for Dual-Blind Face Restoration
• Random Network Distillation as a Diversity Metric for Both Image and Text Generation
• Tessellated Wasserstein Auto-Encoders
• Semantic Editing On Segmentation Map Via Multi-Expansion Loss
• Dynamic Neural Garments
• S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
• A Mean-Field Theory for Kernel Alignment with Random Features in Generative and Discriminative Models
• Generative Models for Security: Attacks, Defenses, and Opportunities
• A Spectral Enabled GAN for Time Series Data Generation
• Separating Content and Style for Unsupervised Image-to-Image Translation
• Unpaired Learning for High Dynamic Range Image Tone Mapping
• Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration
• On the Frequency Bias of Generative Models
• NeurInt : Learning to Interpolate through Neural ODEs
• What and Where to Translate: Local Mask-based Image-to-Image Translation
• Few-Shot Font Generation with Deep Metric Learning
• Localising In Complex Scenes Using Balanced Adversarial Adaptation
• Pixel-wise Dense Detector for Image Inpainting
• Multiclass non-Adversarial Image Synthesis, with Application to Classification from Very Small Sample
• Entropy-regularized optimal transport on multivariate normal and q-normal distributions
• Human Pose Transfer by Adaptive Hierarchical Deformation
• Generate and Verify: Semantically Meaningful Formal Analysis of Neural Network Perception Systems
• Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling
• ArrowGAN : Learning to Generate Videos by Learning Arrow of Time
• Adversarial Machine Learning in Text Analysis and Generation
• Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence
• EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss
• One Shot Audio to Animated Video Generation
• Normalized Diversification
• Domain Adaptation for Learning Generator from Paired Few-Shot Data
• Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples
• Continual Density Ratio Estimation in an Online Setting
• ID-Unet: Iterative Soft and Hard Deformation for View Synthesis
• DeFLOCNet: Deep Image Editing via Flexible Low-level Controls
• Head2HeadFS: Video-based Head Reenactment with Few-shot Learning
• Bridging the Visual Gap: Wide-Range Image Blending
• ReMix: Towards Image-to-Image Translation with Limited Data
• Spatial Content Alignment For Pose Transfer
• Exploiting Relationship for Complex-scene Image Generation
• Training Deep Normalizing Flow Models in Highly Incomplete Data Scenarios with Prior Regularization
• Monte Carlo Simulation of SDEs using GANs
• LI-Net: Large-Pose Identity-Preserving Face Reenactment Network
• Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translation
• Video-to-Video Translation for Visual Speech Synthesis
• An Empirical Study of the Effects of Sample-Mixing Methods for Efficient Training of Generative Adversarial Networks
• Re-designing cities with conditional adversarial networks
• Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation
• APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals
• Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency
• Multi-view Alignment and Generation in CCA via Consistent Latent Encoding
• From Real to Synthetic and Back: Synthesizing Training Data for Multi-Person Scene Understanding
• Nested Scale Editing for Conditional Image Synthesis
• Host-Pathongen Co-evolution Inspired Algorithm Enables Robust GAN Training
• An Edge Information and Mask Shrinking Based Image Inpainting Approach
• PCGAN: Partition-Controlled Human Image Generation
• NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results
• MMCGAN: Generative Adversarial Network with Explicit Manifold Prior
• Face-to-Music Translation Using a Distance-Preserving Generative Adversarial Network with an Auxiliary Discriminator
• MTAdam: Automatic Balancing of Multiple Training Loss Terms
• Strategic Prediction with Latent Aggregative Games
• MCMI: Multi-Cycle Image Translation with Mutual Information Constraints
• Comprehensive Facial Expression Synthesis using Human-Interpretable Language
• Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling
• One-element Batch Training by Moving Window
• Local Stability and Performance of Simple Gradient Penalty mu-Wasserstein GAN
• Toward Zero-Shot Unsupervised Image-to-Image Translation
• Improving Generative Adversarial Networks with Local Coordinate Coding
• Translate the Facial Regions You Like Using Region-Wise Normalization
• Improving Stability of LS-GANs for Audio and Speech Signals
• Semantic View Synthesis
• ByeGlassesGAN: Identity Preserving Eyeglasses Removal for Face Images
• Escaping from Collapsing Modes in a Constrained Space
• 3D Dense Geometry-Guided Facial Expression Synthesis by Adversarial Learning
• Deep Factorised Inverse-Sketching
• Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
• Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training
• Stacked Wasserstein Autoencoder
• Semantic Example Guided Image-to-Image Translation
• Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
• Vehicle Image Generation Going Well with The Surroundings
• Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling
• LinesToFacePhoto: Face Photo Generation from Lines with Conditional Self-Attention Generative Adversarial Network
• Establishing an Evaluation Metric to Quantify Climate Change Image Realism
• Multimodal Image Outpainting With Regularized Normalized Diversification
• Wavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models
• Ensembles of Generative Adversarial Networks for Disconnected Data
• Pixel-wise Conditioning of Generative Adversarial Networks
• Human Annotations Improve GAN Performances
• A novel generative reverse net assisted evolution algorithm for expensive-computational optimizations
• Generating Object Stamps
• Adversarial Code Learning for Image Generation
• A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models
• The Benefits of Pairwise Discriminators for Adversarial Training
• Learning to Inpaint by Progressively Growing the Mask Regions
• Anonymization of labeled TOF-MRA images for brain vessel segmentation using generative adversarial networks
• Backpropagating through Fréchet Inception Distance
• TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator
• LEGAN: Disentangled Manipulation of Directional Lighting and Facial Expressions by Leveraging Human Perceptual Judgements
• Cascaded Refinement Network for Point Cloud Completion with Self-supervision
• Uncertainty in Neural Processes
• Multichannel Generative Language Model: Learning All Possible Factorizations Within and Across Channels
• Joint Wasserstein Distribution Matching
• Synthetic Expressions are Better Than Real for Learning to Detect Facial Actions
• Toward a Generalization Metric for Deep Generative Models
• MUSE: Textual Attributes Guided Portrait Painting Generation
• Enhance Convolutional Neural Networks with Noise Incentive Block
• Efficient Semantic Image Synthesis via Class-Adaptive Normalization
• Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More
• Impressions2Font: Generating Fonts by Specifying Impressions
• Spectral Tensor Train Parameterization of Deep Learning Layers
• Multiple GAN Inversion for Exemplar-based Image-to-Image Translation
• Towards GANs' Approximation Ability
• Generation and Simulation of Yeast Microscopy Imagery with Deep Learning
• Unsupervised Image Transformation Learning via Generative Adversarial Networks
• Generating Multi-type Temporal Sequences to Mitigate Class-imbalanced Problem
• Generative Adversarial Network: Some Analytical Perspectives
• FusedProp: Towards Efficient Training of Generative Adversarial Networks
• Iterative Alignment Flows
• Improved Image Generation via Sparse Modeling
• Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose
• Eccentric Regularization: Minimizing Hyperspherical Energy without explicit projection
• Using Adaptive Gradient for Texture Learning in Single-View 3D Reconstruction
• An Investigation into the Stochasticity of Batch Whitening
• Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement
• Robust Learning in Heterogeneous Contexts
• Conditional Invertible Neural Networks for Diverse Image-to-Image Translation
• SS-CADA: A Semi-Supervised Cross-Anatomy Domain Adaptation for Coronary Artery Segmentation
• Directional GAN: A Novel Conditioning Strategy for Generative Networks
• When Relation Networks meet GANs: Relation GANs with Triplet Loss
• Stein Latent Optimization for Generative Adversarial Networks
• FoCL: Feature-Oriented Continual Learning for Generative Models
• Hierarchical Modes Exploring in Generative Adversarial Networks
• Learning to See by Looking at Noise
• Local AdaGrad-Type Algorithm for Stochastic Convex-Concave Optimization
• The Implicit Metropolis-Hastings Algorithm
• Dual Projection Generative Adversarial Networks for Conditional Image Generation
• Neural Scene Decoration from a Single Photograph
• Blind Image Decomposition
• Towards Representation Learning for Atmospheric Dynamics
• LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation
• Quantifying point cloud realism through adversarially learned latent representations
• Probabilistic Autoencoder using Fisher Information
• Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps
• Dynamic Variational Autoencoders for Visual Process Modeling
• On the Limitations of Multimodal VAEs
• Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE
• Can semi-supervised learning reduce the amount of manual labelling required for effective radio galaxy morphology classification?
• Generative Adversarial Network for Probabilistic Forecast of Random Dynamical System
• EdiBERT, a generative model for image editing
• Layered Controllable Video Generation
• Self-supervised Correlation Mining Network for Person Image Generation
• Dist-GAN: An Improved GAN using Distance Constraints
• A moment-matching metric for latent variable generative models
• Contrastive Feature Loss for Image Prediction
• Data Augmentation using Random Image Cropping for High-resolution Virtual Try-On (VITON-CROP)
• Xp-GAN: Unsupervised Multi-object Controllable Video Generation
• Invexifying Regularization of Non-Linear Least-Squares Problems
• Generative Adversarial Networks for Astronomical Images Generation
• Delving into Rectifiers in Style-Based Image Translation
• MixSyn: Learning Composition and Style for Multi-Source Image Synthesis
• Gated SwitchGAN for multi-domain facial image translation
• Learning Wildfire Model from Incomplete State Observations
• Trust the Critics: Generatorless and Multipurpose WGANs with Initial Convergence Guarantees
• Information Compensation for Deep Conditional Generative Networks
• SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Editing
• Forward Operator Estimation in Generative Models with Kernel Transfer Operators
• 3D-Aware Semantic-Guided Generative Model for Human Synthesis
• Investigating Conceptual Blending of a Diffusion Model for Improving Nonword-to-Image Generation
• Stay Positive: Non-Negative Image Synthesis for Augmented Reality
• Synthesizing Photorealistic Images with Deep Generative Learning
• Learning Image Attacks toward Vision Guided Autonomous Vehicles
• Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation
• SmartPatch: Improving Handwritten Word Imitation with Patch Discriminators
• Neural Wireframe Renderer: Learning Wireframe to Image Translations
• Deep Automodulators
• CAMS: Color-Aware Multi-Style Transfer
• On the Generative Utility of Cyclic Conditionals
• Barcode Method for Generative Model Evaluation driven by Topological Data Analysis
• Composition and decomposition of GANs
• Natural Image Manipulation for Autoregressive Models Using Fisher Scores
• MOC-GAN: Mixing Objects and Captions to Generate Realistic Images
• Virtual Conditional Generative Adversarial Networks
• ViT-Inception-GAN for Image Colourising
• Noise Robust Generative Adversarial Networks
• Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
• Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation
• Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis
• Class Balancing GAN with a Classifier in the Loop
• Image-to-Image Translation of Synthetic Samples for Rare Classes
• Unsupervised Learning of Depth and Depth-of-Field Effect from Natural Images with Aperture Rendering Generative Adversarial Networks
• Fostering Diversity in Spatial Evolutionary Generative Adversarial Networks
• Face Sketch Synthesis via Semantic-Driven Generative Adversarial Network
• Bridging the Gap Between $f$-GANs and Wasserstein GANs
• Viscos Flows: Variational Schur Conditional Sampling With Normalizing Flows
• Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks
• Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning
• NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
• Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation
• Generative Adversarial Learning via Kernel Density Discrimination
• Controlled AutoEncoders to Generate Faces from Voices
• A Systematical Solution for Face De-identification
• Inducing Hierarchical Compositional Model by Sparsifying Generator Network
• Synthetic Periocular Iris PAI from a Small Set of Near-Infrared-Images
• CanvasVAE: Learning to Generate Vector Graphic Documents
• UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing
• From Continuity to Editability: Inverting GANs with Consecutive Images
• Identifying and Exploiting Structures for Reliable Deep Learning
• BooVAE: Boosting Approach for Continual Learning of VAE
• Visual-Relation Conscious Image Generation from Structured-Text
• Transferring Knowledge with Attention Distillation for Multi-Domain Image-to-Image Translation
• Zoom, Enhance! Measuring Surveillance GAN Up-sampling
• Multi-Attributed and Structured Text-to-Face Synthesis
• Coulomb Autoencoders
• StackGAN: Facial Image Generation Optimizations
• Instance-Conditioned GAN
• FA-GAN: Feature-Aware GAN for Text to Image Synthesis
• SetGAN: Improving the stability and diversity of generative models through a permutation invariant architecture
• Sparse to Dense Motion Transfer for Face Image Animation
• Stereo Video Reconstruction Without Explicit Depth Maps for Endoscopic Surgery
• Unaligned Image-to-Image Translation by Learning to Reweight
• Physical Context and Timing Aware Sequence Generating GANs
• Collaging Class-specific GANs for Semantic Image Synthesis
• Neural Network based Explicit Mixture Models and Expectation-maximization based Learning
• Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation
• LSC-GAN: Latent Style Code Modeling for Continuous Image-to-image Translation
• Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency
• Harnessing the Conditioning Sensorium for Improved Image Translation
• GILBO: One Metric to Measure Them All
• Diffusion Normalizing Flow
• Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis
• MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
• AE-StyleGAN: Improved Training of Style-Based Auto-Encoders
• Self-Supervised Object Detection via Generative Image Synthesis
• A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation
• Multi-attribute Pizza Generator: Cross-domain Attribute Control with Conditional StyleGAN
• An Empirical Study on GANs with Margin Cosine Loss and Relativistic Discriminator