Denoising Diffusion Probabilistic Models

Abstract

We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN. Our implementation is available at https://github.com/hojonathanho/diffusion

References in corpus (28)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• WaveNet: A Generative Model for Raw Audio
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Conditional Image Generation with PixelCNN Decoders
• Wide Residual Networks
• Pixel Recurrent Neural Networks
• NICE: Non-linear Independent Components Estimation
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Variational Inference with Normalizing Flows
• Generative Modeling by Estimating Gradients of the Data Distribution
• Training Generative Adversarial Networks with Limited Data
• Density estimation using Real NVP
• Generating Long Sequences with Sparse Transformers
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
• A Theory of Generative ConvNet
• Improved Techniques for Training Score-Based Generative Models
• BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
• Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model
• A-NICE-MC: Adversarial Training for MCMC
• Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling
• Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
• Stochastic Normalizing Flows
• Evaluating Lossy Compression Rates of Deep Generative Models
• Learning to Generate Samples from Noise through Infusion Training
• Predictive Sampling with Forecasting Autoregressive Models
• VQ-DRAW: A Sequential Discrete VAE

Cited by in corpus (339)

• On the Opportunities and Risks of Foundation Models
• Diffusion Models Beat GANs on Image Synthesis
• Diffusion Models in Vision: A Survey
• Generative AI
• Blended Diffusion for Text-driven Editing of Natural Images
• A Comprehensive Survey on Deep Graph Representation Learning
• Compute Trends Across Three Eras of Machine Learning
• Towards Small Object Editing: A Benchmark Dataset and A Training-Free Approach
• Variational Diffusion Models
• Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review
• Speech Enhancement and Dereverberation with Diffusion-based Generative Models
• Diffusion Probabilistic Models beat GANs on Medical Images
• A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction
• CLIP-Mesh: Generating textured meshes from text using pretrained image-text models
• A Survey on Neural Speech Synthesis
• Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
• Generative AI in the Construction Industry: Opportunities & Challenges
• SpaText: Spatio-Textual Representation for Controllable Image Generation
• VideoGPT: Video Generation using VQ-VAE and Transformers
• Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models
• StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
• At the Dawn of Generative AI Era: A Tutorial-cum-Survey on New Frontiers in 6G Wireless Intelligence
• DiffWave: A Versatile Diffusion Model for Audio Synthesis
• Locally Attentional SDF Diffusion for Controllable 3D Shape Generation
• CBCT-Based Synthetic CT Image Generation Using Conditional Denoising Diffusion Probabilistic Model
• Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges
• A survey on GANs for computer vision: Recent research, analysis and taxonomy
• Diffusion Models, Image Super-Resolution And Everything: A Survey
• DiffEdit: Diffusion-based semantic image editing with mask guidance
• Time Series Diffusion Method: A Denoising Diffusion Probabilistic Model for Vibration Signal Generation
• Denoising Diffusion Implicit Models
• Differentiable Augmentation for Data-Efficient GAN Training
• SpectralDiff: A Generative Framework for Hyperspectral Image Classification with Diffusion Models
• SAR Despeckling using a Denoising Diffusion Probabilistic Model
• PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions
• Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties
• DeScoD-ECG: Deep Score-Based Diffusion Model for ECG Baseline Wander and Noise Removal
• Adaptive Latent Diffusion Model for 3D Medical Image to Image Translation: Multi-modal Magnetic Resonance Imaging Study
• Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow
• Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement
• How to Train Your Energy-Based Models
• Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
• CLE Diffusion: Controllable Light Enhancement Diffusion Model
• LDMVFI: Video Frame Interpolation with Latent Diffusion Models
• A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources
• A Diffusion model for POI recommendation
• 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
• "An Adapt-or-Die Type of Situation": Perception, Adoption, and Use of Text-To-Image-Generation AI by Game Industry Professionals
• Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model
• BINN: A deep learning approach for computational mechanics problems based on boundary integral equations
• Deep Diffusion Models for Seismic Processing
• Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
• Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
• Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
• Synthetically Enhanced: Unveiling Synthetic Data's Potential in Medical Imaging Research
• On Fast Sampling of Diffusion Probabilistic Models
• A Prompt Log Analysis of Text-to-Image Generation Systems
• Generative Discovery of Novel Chemical Designs using Diffusion Modeling and Transformer Deep Neural Networks with Application to Deep Eutectic Solvents
• An Interdisciplinary Survey on Origin-destination Flows Modeling: Theory and Techniques
• Spatio-temporal Diffusion Point Processes
• NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates
• Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• medigan: a Python library of pretrained generative models for medical image synthesis
• FDiff-Fusion:Denoising diffusion fusion network based on fuzzy learning for 3D medical image segmentation
• Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources
• Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey
• Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
• Denoising diffusion-based MRI to CT image translation enables automated spinal segmentation
• WaveGrad: Estimating Gradients for Waveform Generation
• A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective
• PlantoGraphy: Incorporating Iterative Design Process into Generative Artificial Intelligence for Landscape Rendering
• Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
• ControlMat: A Controlled Generative Approach to Material Capture
• SGDiff: A Style Guided Diffusion Model for Fashion Synthesis
• Guided Image Synthesis via Initial Image Editing in Diffusion Model
• SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
• Challenges for Monocular 6D Object Pose Estimation in Robotics
• Vector Quantized Diffusion Model for Text-to-Image Synthesis
• MatFusion: A Generative Diffusion Model for SVBRDF Capture
• A Review on Low-Dose Emission Tomography Post-Reconstruction Denoising with Neural Network Approaches
• Noise Estimation for Generative Diffusion Models
• FS-Diff: Semantic guidance and clarity-aware simultaneous multimodal image fusion and super-resolution
• CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
• Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion
• From Screens to Scenes: A Survey of Embodied AI in Healthcare
• Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
• Con-CDVAE: A method for the conditional generation of crystal structures
• The Entoptic Field Camera as Metaphor-Driven Research-through-Design with AI Technologies
• Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
• On the design space between molecular mechanics and machine learning force fields
• MatFuse: Controllable Material Generation with Diffusion Models
• Generative diffusion in very large dimensions
• Latent Diffusion Model for Conditional Reservoir Facies Generation
• Systematic Review on Learning-based Spectral CT
• The DiffuseStyleGesture+ entry to the GENEA Challenge 2023
• Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
• Denoising diffusion probabilistic models for probabilistic energy forecasting
• Adversarial score matching and improved sampling for image generation
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation
• FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models
• Improved Contrastive Divergence Training of Energy Based Models
• Artifact Reduction in 3D and 4D Cone-beam Computed Tomography Images with Deep Learning -- A Review
• Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence
• MAM-E: Mammographic synthetic image generation with diffusion models
• A Transformer-based Diffusion Probabilistic Model for Heart Rate and Blood Pressure Forecasting in Intensive Care Unit
• 360-Degree Panorama Generation from Few Unregistered NFoV Images
• EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning
• CT-Mamba: A Hybrid Convolutional State Space Model for Low-Dose CT Denoising
• Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective
• Diffusion Probabilistic Models for 3D Point Cloud Generation
• Fast Dynamic 1D Simulation of Divertor Plasmas with Neural PDE Surrogates
• RNDiff: Rainfall nowcasting with Condition Diffusion Model
• Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region
• Self-Supervised Variational Auto-Encoders
• FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection
• Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection
• Guided Reconstruction with Conditioned Diffusion Models for Unsupervised Anomaly Detection in Brain MRIs
• Review of end-to-end speech synthesis technology based on deep learning
• Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolution
• Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution
• PanoGAN A Deep Generative Model for Panoramic Dental Radiographs
• Gotta Go Fast When Generating Data with Score-Based Models
• Score-Based Generative Models for PET Image Reconstruction
• A Study on Speech Enhancement Based on Diffusion Probabilistic Model
• DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM
• Bi-fidelity Variational Auto-encoder for Uncertainty Quantification
• Gradient Step Denoiser for convergent Plug-and-Play
• Painterly Image Harmonization using Diffusion Model
• A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Research
• StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis
• TexSliders: Diffusion-Based Texture Editing in CLIP Space
• Face Morphing Attack Detection with Denoising Diffusion Probabilistic Models
• UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons
• 4D Facial Expression Diffusion Model
• Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model
• Non Gaussian Denoising Diffusion Models
• 3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation
• Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution
• Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields
• RDIS: Random Drop Imputation with Self-Training for Incomplete Time Series Data
• The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers
• Coarse-to-Fine Proposal Refinement Framework for Audio Temporal Forgery Detection and Localization
• Deep Generative Imputation Model for Missing Not At Random Data
• Boosting GUI Prototyping with Diffusion Models
• Learning Energy-Based Models by Diffusion Recovery Likelihood
• Structured Variational Inference for Simulating Populations of Radio Galaxies
• DriveSceneGen: Generating Diverse and Realistic Driving Scenarios from Scratch
• ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models
• Iterative $\alpha$-(de)Blending: a Minimalist Deterministic Diffusion Model
• Constrained CycleGAN for Effective Generation of Ultrasound Sector Images of Improved Spatial Resolution
• Automatic Differentiation-based Full Waveform Inversion with Flexible Workflows
• EASI-Tex: Edge-Aware Mesh Texturing from Single Image
• UMat: Uncertainty-Aware Single Image High Resolution Material Capture
• ProbTalk3D: Non-Deterministic Emotion Controllable Speech-Driven 3D Facial Animation Synthesis Using VQ-VAE
• Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data
• Virtual Staining of Label-Free Tissue in Imaging Mass Spectrometry
• SegDiff: Image Segmentation with Diffusion Probabilistic Models
• DiffMark: Diffusion-based Robust Watermark Against Deepfakes
• The stochastic digital human is now enrolling for in silico imaging trials -- Methods and tools for generating digital cohorts
• Unsupervisedly Prompting AlphaFold2 for Few-Shot Learning of Accurate Folding Landscape and Protein Structure Prediction
• Turbulence Scaling from Deep Learning Diffusion Generative Models
• LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech
• 3D Brain and Heart Volume Generative Models: A Survey
• Style Transfer with Diffusion Models for Synthetic-to-Real Domain Adaptation
• Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
• License Plate Super-Resolution Using Diffusion Models
• Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
• Bilateral Denoising Diffusion Models
• Normalizing flows as an enhanced sampling method for atomistic supercooled liquids
• Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations
• SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection
• DRUM: Diffusion-based runoff model for probabilistic flood forecasting
• Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias
• Data Augmentation in Earth Observation: A Diffusion Model Approach
• Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement
• FCBoost-Net: A Generative Network for Synthesizing Multiple Collocated Outfits via Fashion Compatibility Boosting
• Context-Aware Mutual Learning for Blind Image Inpainting and Beyond
• Transforming Agency. On the mode of existence of Large Language Models
• Generative artificial intelligence in dentistry: Current approaches and future challenges
• Towards Robust Neural Networks via Orthogonal Diversity
• Leveraging Labelled Data Knowledge: A Cooperative Rectification Learning Network for Semi-supervised 3D Medical Image Segmentation
• Frequency-Controlled Diffusion Model for Versatile Text-Guided Image-to-Image Translation
• Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models
• Parameter-Efficient Learning for Text-to-Speech Accent Adaptation
• HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization
• A Contrastive Learning Approach for Training Variational Autoencoder Priors
• Diffusion-Augmented Depth Prediction with Sparse Annotations
• Riemannian Denoising Diffusion Probabilistic Models
• A Flow-based Truncated Denoising Diffusion Model for Super-resolution Magnetic Resonance Spectroscopic Imaging
• VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics
• Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimes
• PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images
• Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking
• Surgical Text-to-Image Generation
• Reflection-Equivariant Diffusion for 3D Structure Determination from Isotopologue Rotational Spectra in Natural Abundance
• Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models
• Diffusion-Based Audio Inpainting
• LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance
• Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Discrete-Time Conditional Gaussian Koopman Network
• Human Image Generation: A Comprehensive Survey
• Diffusion Priors In Variational Autoencoders
• Synomaly Noise and Multi-Stage Diffusion: A Novel Approach for Unsupervised Anomaly Detection in Medical Images
• Stylized Face Sketch Extraction via Generative Prior with Limited Data
• Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE
• Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET
• Global Search for Optimal Low Thrust Spacecraft Trajectories using Diffusion Models and the Indirect Method
• DiffuSETS: 12-lead ECG Generation Conditioned on Clinical Text Reports and Patient-Specific Information
• SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization
• Diff-TTS: A Denoising Diffusion Model for Text-to-Speech
• Unraveling the Potential of Diffusion Models in Small Molecule Generation
• Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks
• Stop-and-go wave super-resolution reconstruction via iterative refinement
• Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach
• Inverse problem regularization with hierarchical variational autoencoders
• Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction
• Exploring Multi-Modal Control in Music-Driven Dance Generation
• Improved HER2 Tumor Segmentation with Subtype Balancing using Deep Generative Networks
• VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
• Predicting Change, Not States: An Alternate Framework for Neural PDE Surrogates
• CLIP4Sketch: Enhancing Sketch to Mugshot Matching through Dataset Augmentation using Diffusion Models
• ZePo: Zero-Shot Portrait Stylization with Faster Sampling
• Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)
• Anytime Sampling for Autoregressive Models via Ordered Autoencoding
• Denoising Diffusion Gamma Models
• Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
• Chunked Autoregressive GAN for Conditional Waveform Synthesis
• Score-matching neural networks for improved multi-band source separation
• Retinal OCT Synthesis with Denoising Diffusion Probabilistic Models for Layer Segmentation
• ExpGest: Expressive Speaker Generation Using Diffusion Model and Hybrid Audio-Text Guidance
• Shape-Guided Clothing Warping for Virtual Try-On
• DiffDefense: Defending against Adversarial Attacks via Diffusion Models
• WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
• SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction
• Pathology Synthesis of 3D-Consistent Cardiac MR Images using 2D VAEs and GANs
• Optimal Linear Subspace Search: Learning to Construct Fast and High-Quality Schedulers for Diffusion Models
• SEEDS: Exponential SDE Solvers for Fast High-Quality Sampling from Diffusion Models
• Artificial Inductive Bias for Synthetic Tabular Data Generation in Data-Scarce Scenarios
• Generative Design of Crystal Structures by Point Cloud Representations and Diffusion Model
• Approximating Optimal Morphing Attacks using Template Inversion
• A 28.6 mJ/iter Stable Diffusion Processor for Text-to-Image Generation with Patch Similarity-based Sparsity Augmentation and Text-based Mixed-Precision
• S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral Domain
• Self-Supervised Adversarial Diffusion Models for Fast MRI Reconstruction
• Comprehensive Dataset of Synthetic and Manipulated Overhead Imagery for Development and Evaluation of Forensic Tools
• RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects
• Latent Iterative Refinement for Modular Source Separation
• PartIR: Composing SPMD Partitioning Strategies for Machine Learning
• AniFaceDiff: Animating Stylized Avatars via Parametric Conditioned Diffusion Models
• Improved Autoregressive Modeling with Distribution Smoothing
• Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation
• A Flow-Based Model for Conditional and Probabilistic Electricity Consumption Profile Generation and Prediction
• Untrained neural networks can demonstrate memorization-independent abstract reasoning
• Generative Unfolding with Distribution Mapping
• ID-Booth: Identity-consistent Face Generation with Diffusion Models
• Recursive Variational Autoencoders for 3D Blood Vessel Generative Modeling
• Counterfactual Generative Models for Time-Varying Treatments
• Learning dissection trajectories from expert surgical videos via imitation learning with equivariant diffusion
• Recursive Neural Programs: Variational Learning of Image Grammars and Part-Whole Hierarchies
• LVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation
• Content-Aware Preserving Image Generation
• Dreaming of Electrical Waves: Generative Modeling of Cardiac Excitation Waves using Diffusion Models
• Context-Aware Indoor Point Cloud Object Generation through User Instructions
• Zero Shot Molecular Generation via Similarity Kernels
• Face Aging via Diffusion-based Editing
• Human Pose Transfer with Augmented Disentangled Feature Consistency
• A Mathematical Framework for Learning Probability Distributions
• Stochastic Super-resolution of Cosmological Simulations with Denoising Diffusion Models
• Reliable Multi-modal Medical Image-to-image Translation Independent of Pixel-wise Aligned Data
• 3D latent diffusion models for parameterizing and history matching multiscenario facies systems
• Asymmetric discrete random walk and drift-diffusion with unequal jump times, lengths, and probabilities
• Novel Concept-Oriented Synthetic Data approach for Training Generative AI-Driven Crystal Grain Analysis Using Diffusion Model
• Density Ratio Estimation via Infinitesimal Classification
• Score-based Diffusion Models for Bayesian Image Reconstruction
• Learning multi-scale local conditional probability models of images
• Generating Multiphase Fluid Configurations in Fractures using Diffusion Models
• DiffBlender: Composable and Versatile Multimodal Text-to-Image Diffusion Models
• Image-Text Out-Of-Context Detection Using Synthetic Multimodal Misinformation
• Adaptive and Iterative Point Cloud Denoising with Score-Based Diffusion Model
• PAC-Bayesian Soft Actor-Critic Learning
• Cycle-Constrained Adversarial Denoising Convolutional Network for PET Image Denoising: Multi-Dimensional Validation on Large Datasets with Reader Study and Real Low-Dose Data
• Interpolating between sampling and variational inference with infinite stochastic mixtures
• The Quest for Early Detection of Retinal Disease: 3D CycleGAN-based Translation of Optical Coherence Tomography into Confocal Microscopy
• EvoText: Enhancing Natural Language Generation Models via Self-Escalation Learning for Up-to-Date Knowledge and Improved Performance
• Large, fast and accurate HI intensity maps with latent overlap diffusion
• Harmonic Path Integral Diffusion
• Language Guided Adversarial Purification
• Fokker-Planck Score Learning: Efficient Free-Energy Estimation under Periodic Boundary Conditions
• Path and Bone-Contour Regularized Unpaired MRI-to-CT Translation
• Differentiable Surrogate for Detector Simulation and Design with Diffusion Models
• A Conditional Point Cloud Diffusion Model for Deformable Liver Motion Tracking Via a Single Arbitrarily-Angled X-ray Projection
• Pre-training for Recommendation Unlearning
• Semantics-Aware Human Motion Generation from Audio Instructions
• Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding
• ReShader: View-Dependent Highlights for Single Image View-Synthesis
• FlexiD-Fuse: Flexible number of inputs multi-modal medical image fusion based on diffusion model
• Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification
• Uncertainties of Satellite-based Essential Climate Variables from Deep Learning
• DSAP: Analyzing Bias Through Demographic Comparison of Datasets
• Turbulent Injection assisted by Diffusion Models for Scale Resolving Simulations
• One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models
• Hand-Shadow Poser
• Explaining the effects of non-convergent sampling in the training of Energy-Based Models
• Quantum data generation in a denoising model with multiscale entanglement renormalization network
• Synthetic Data Generation for Classifying Electrophysiological and Morpho-Electrophysiological Neurons from Mouse Visual Cortex
• Deep image prior inpainting of ancient frescoes in the Mediterranean Alpine arc
• Model See Model Do: Speech-Driven Facial Animation with Style Control
• Lattice Protein Folding with Variational Annealing
• EMID: An Emotional Aligned Dataset in Audio-Visual Modality
• Evaluating the plausibility of synthetic images for improving automated endoscopic stone recognition
• Synthesising Activity Participations and Scheduling with Deep Generative Machine Learning
• CoSTI: Consistency Models for (a faster) Spatio-Temporal Imputation
• IgCONDA-PET: Weakly-Supervised PET Anomaly Detection using Implicitly-Guided Attention-Conditional Counterfactual Diffusion Modeling -- a Multi-Center, Multi-Cancer, and Multi-Tracer Study
• Radio Halo Detection in MWA Data using Deep Neural Networks and Generative Data Augmentation
• Monte Carlo guided Diffusion for Bayesian linear inverse problems
• ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a protein language diffusion model
• Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation
• Stochastic Super-Resolution For Gaussian Textures
• D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
• Multimodal Laryngoscopic Video Analysis for Assisted Diagnosis of Vocal Fold Paralysis
• BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics
• ESCT3D: Efficient and Selectively Controllable Text-Driven 3D Content Generation with Gaussian Splatting
• NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
• RBM-Flow and D-Flow: Invertible Flows with Discrete Energy Base Spaces
• Beyond In-Place Corruption: Insertion and Deletion In Denoising Probabilistic Models
• Improving Compositionality of Neural Networks by Decoding Representations to Inputs
• Conditionally Strongly Log-Concave Generative Models
• Diffusion Normalizing Flow
• Semantic Generative Augmentations for Few-Shot Counting
• Zero-Shot Translation using Diffusion Models
• Neural Differential Appearance Equations
• EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss
• Equivariant plug-and-play image reconstruction
• Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
• GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models
• Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet Diffusion
• Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis
• Lane Graph Extraction from Aerial Imagery via Lane Segmentation Refinement with Diffusion Models