Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts

Abstract

Automatic image synthesis research has been rapidly growing with deep networks getting more and more expressive. In the last couple of years, we have observed images of digits, indoor scenes, birds, chairs, etc. being automatically generated. The expressive power of image generators have also been enhanced by introducing several forms of conditioning variables such as object names, sentences, bounding box and key-point locations. In this work, we propose a novel deep conditional generative adversarial network architecture that takes its strength from the semantic layout and scene attributes integrated as conditioning variables. We show that our architecture is able to generate realistic outdoor scene images under different conditions, e.g. day-night, sunny-foggy, with clear object boundaries.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• DRAW: A Recurrent Neural Network For Image Generation
• Generating Videos with Scene Dynamics
• Deep Convolutional Inverse Graphics Network
• Semantic Understanding of Scenes through the ADE20K Dataset

Cited by in corpus (48)

• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• How Generative Adversarial Networks and Their Variants Work: An Overview
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• Image De-raining Using a Conditional Generative Adversarial Network
• Semantic Object Accuracy for Generative Text-to-Image Synthesis
• Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
• Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis
• Generating Multiple Objects at Spatially Distinct Locations
• Landmark Assisted CycleGAN for Cartoon Face Generation
• Learning Generative Models across Incomparable Spaces
• Privacy-Protection Drone Patrol System based on Face Anonymization
• Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
• Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss
• Text2Scene: Generating Compositional Scenes from Textual Descriptions
• DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)
• Modular Generative Adversarial Networks
• Thermal Infrared Colorization via Conditional Generative Adversarial Network
• Image Generation from Layout
• PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
• Diverse Image Synthesis from Semantic Layouts via Conditional IMLE
• Adversarial Video Compression Guided by Soft Edge Detection
• Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANs
• Attention-GAN for Object Transfiguration in Wild Images
• SwapText: Image Based Texts Transfer in Scenes
• Text Guided Person Image Synthesis
• End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image
• Attribute-guided image generation from layout
• MIXGAN: Learning Concepts from Different Domains for Mixture Generation
• StyleRemix: An Interpretable Representation for Neural Image Style Transfer
• Towards Learning a Self-inverse Network for Bidirectional Image-to-image Translation
• Guiding Intelligent Surveillance System by learning-by-synthesis gaze estimation
• PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
• Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks
• GANILLA: Generative Adversarial Networks for Image to Illustration Translation
• PanoDR: Spherical Panorama Diminished Reality for Indoor Scenes
• High Diversity Attribute Guided Face Generation with GANs
• Global Image Sentiment Transfer
• Understanding the Role of Adversarial Regularization in Supervised Learning
• LinesToFacePhoto: Face Photo Generation from Lines with Conditional Self-Attention Generative Adversarial Network
• Image Sentiment Transfer
• Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks
• Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis
• Harnessing the Conditioning Sensorium for Improved Image Translation
• Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood Estimation
• Inner Space Preserving Generative Pose Machine
• Instance Map based Image Synthesis with a Denoising Generative Adversarial Network