ICCV 2019 accepted papers on Image generation
128 of the 1,075 papers accepted at ICCV 2019 (11.9%) are on Image generation, compared with 11.0% at ICCV 2017. They fall into 6 topics.
See ICCV 2019 in the interactive map
Submitting to ICCV? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Image restoration · 38 papers
- GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing (1,138 citations)
- Real Image Denoising With Feature Attention (793 citations)
- Recursive Cascaded Networks for Unsupervised Medical Image Registration (343 citations)
- Image Inpainting With Learnable Bidirectional Attention Maps (292 citations)
- Variable Rate Deep Image Compression With a Conditional Autoencoder (283 citations)
- Mask-ShadowGAN: Learning to Remove Shadows From Unpaired Data (271 citations)
- Shadow Removal via Shadow Image Decomposition (240 citations)
- Self-Guided Network for Fast Image Denoising (209 citations)
- Indices Matter: Learning to Index for Deep Image Matting (207 citations)
- Localization of Deep Inpainting Using High-Pass Fully Convolutional Network (188 citations)
- Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation (174 citations)
- Deep Learning for Seeing Through Window With Raindrops (159 citations)
and 26 more in the interactive map.
Editing and style transfer · 30 papers
- Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space? (1,090 citations)
- Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (709 citations)
- Few-Shot Unsupervised Image-to-Image Translation (688 citations)
- StructureFlow: Image Inpainting via Structure-Aware Appearance Flow (419 citations)
- Photorealistic Style Transfer via Wavelet Transforms (417 citations)
- ClothFlow: A Flow-Based Model for Clothed Person Generation (274 citations)
- Towards Multi-Pose Guided Virtual Try-On Network (227 citations)
- VTNFP: An Image-Based Virtual Try-On Network With Body and Clothing Feature Preservation (176 citations)
- Content and Style Disentanglement for Artistic Style Transfer (170 citations)
- Image Generation From Small Datasets via Batch Statistics Adaptation (170 citations)
- Detecting Photoshopped Faces by Scripting Photoshop (147 citations)
- RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes (142 citations)
and 18 more in the interactive map.
GANs · 27 papers
- DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better (1,226 citations)
- SinGAN: Learning a Generative Model From a Single Natural Image (968 citations)
- Generative Adversarial Networks for Extreme Learned Image Compression (626 citations)
- Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints (530 citations)
- Data-Free Learning of Student Networks (389 citations)
- Seeing What a GAN Cannot Generate (347 citations)
- SC-FEGAN: Face Editing Generative Adversarial Network With User's Sketch and Color (345 citations)
- GANalyze: Toward Visual Definitions of Cognitive Image Properties (316 citations)
- Generative Adversarial Minority Oversampling (251 citations)
- Progressive Reconstruction of Visual Structure for Image Inpainting (197 citations)
- ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal (181 citations)
- InGAN: Capturing and Retargeting the "DNA" of a Natural Image (159 citations)
and 15 more in the interactive map.
Super-resolution · 16 papers
- PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization (1,297 citations)
- Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model (649 citations)
- RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution (421 citations)
- Universally Slimmable Networks and Improved Training Techniques (390 citations)
- SROBB: Targeted Perceptual Loss for Single Image Super-Resolution (176 citations)
- Kernel Modeling Super-Resolution on Real Low-Resolution Images (170 citations)
- Embedded Block Residual Network: A Recursive Restoration Model for Single-Image Super-Resolution (144 citations)
- Deep Blind Hyperspectral Image Fusion (137 citations)
- Learning Filter Basis for Convolutional Neural Network Compression (105 citations)
- Wavelet Domain Style Transfer for an Effective Perception-Distortion Tradeoff in Single Image Super-Resolution (98 citations)
- Guided Super-Resolution As Pixel-to-Pixel Transformation (90 citations)
- Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks (74 citations)
and 4 more in the interactive map.
Autoregressive and latent generation · 9 papers
- FaceForensics++: Learning to Detect Manipulated Facial Images (3,635 citations)
- Free-Form Image Inpainting With Gated Convolution (2,164 citations)
- Coherent Semantic Attention for Image Inpainting (429 citations)
- Meta-Sim: Learning to Generate Synthetic Datasets (235 citations)
- XRAI: Better Attributions Through Regions (220 citations)
- Very Long Natural Scenery Image Prediction by Outpainting (102 citations)
- Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning (60 citations)
- DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer (50 citations)
- Conditional Recurrent Flow: Conditional Generation of Longitudinal Samples With Applications to Neuroimaging (13 citations)
Text-to-image diffusion · 8 papers
- Unsupervised Pre-Training of Image Features on Non-Curated Data (262 citations)
- LayoutVAE: Stochastic Scene Layout Generation From a Label Set (168 citations)
- Improved Techniques for Training Adaptive Deep Networks (146 citations)
- Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction (103 citations)
- FiNet: Compatible and Diverse Fashion Image Inpainting (93 citations)
- DSIC: Deep Stereo Image Compression (58 citations)
- Dual Adversarial Inference for Text-to-Image Synthesis (39 citations)
- Large-Scale Tag-Based Font Retrieval With Generative Feature Learning (25 citations)
