ECCV 2020 accepted papers on Image generation
151 of the 1,358 papers accepted at ECCV 2020 (11.1%) are on Image generation, compared with 11.9% at ECCV 2018. They fall into 6 topics.
See ECCV 2020 in the interactive map
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 · 43 papers
- Learning Enriched Features for Real Image Restoration and Enhancement (1,121 citations)
- Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms (426 citations)
- Defocus Deblurring Using Dual-Pixel Data (273 citations)
- Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation (269 citations)
- Spatial-Adaptive Network for Single Image Denoising (192 citations)
- Unpaired Learning of Deep Image Denoising (188 citations)
- Physics-based Feature Dehazing Networks (175 citations)
- Wavelet-Based Dual-Branch Network for Image Demoiréing (138 citations)
- Practical Deep Raw Image Denoising on Mobile Devices (133 citations)
- Conditional Sequential Modulation for Efficient Global Image Retouching (128 citations)
- Quantization Guided JPEG Artifact Correction (118 citations)
- Guided Deep Decoder: Unsupervised Image Pair Fusion (116 citations)
and 31 more in the interactive map.
Editing and style transfer · 38 papers
- Contrastive Learning for Unpaired Image-to-Image Translation (1,682 citations)
- Blind Face Restoration via Deep Multi-scale Component Dictionaries (204 citations)
- StyleGAN2 Distillation for Feed-forward Image Manipulation (158 citations)
- Unpaired Image-to-Image Translation using Adversarial Consistency Loss (145 citations)
- TSIT: A Simple and Versatile Framework for Image-to-Image Translation (134 citations)
- Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On (120 citations)
- Few-shot Compositional Font Generation with Dual Memory (111 citations)
- ForkGAN: Seeing into the Rainy Night (111 citations)
- COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder (88 citations)
- CONFIG: Controllable Neural Face Image Generation (83 citations)
- Explainable Face Recognition (83 citations)
- TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images (78 citations)
and 26 more in the interactive map.
Super-resolution · 27 papers
- Single Image Super-Resolution via a Holistic Attention Network (866 citations)
- SRFlow: Learning the Super-Resolution Space with Normalizing Flow (409 citations)
- LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block (377 citations)
- Component Divide-and-Conquer for Real-World Image Super-Resolution (301 citations)
- Spatial-Angular Interaction for Light Field Image Super-Resolution (228 citations)
- Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution (181 citations)
- High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling (175 citations)
- PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration (170 citations)
- Scene Text Image Super-resolution in the wild (170 citations)
- Learning with Privileged Information for Efficient Image Super-Resolution (146 citations)
- PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution Unit (97 citations)
- Fast Adaptation to Super-Resolution Networks via Meta-Learning (92 citations)
and 15 more in the interactive map.
GANs · 27 papers
- In-Domain GAN Inversion for Real Image Editing (560 citations)
- XingGAN for Person Image Generation (199 citations)
- Generative Low-bitwidth Data Free Quantization (143 citations)
- Lifespan Age Transformation Synthesis (141 citations)
- HardGAN: A Haze-Aware Representation Distillation GAN for Single Image Dehazing (122 citations)
- GIQA: Generated Image Quality Assessment (92 citations)
- Global and Local Enhancement Networks for Paired and Unpaired Image Enhancement (77 citations)
- GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework (75 citations)
- SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects (75 citations)
- High-Fidelity Synthesis with Disentangled Representation (65 citations)
- GAN-based Garment Generation Using Sewing Pattern Images (50 citations)
- Inclusive GAN: Improving Data and Minority Coverage in Generative Models (49 citations)
and 15 more in the interactive map.
Autoregressive and latent generation · 9 papers
- What makes fake images detectable? Understanding properties that generalize (388 citations)
- Neural Design Network: Graphic Layout Generation with Constraints (142 citations)
- Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes (140 citations)
- Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach (116 citations)
- PieNet: Personalized Image Enhancement Network (57 citations)
- You Are Here: Geolocation by Embedding Maps and Images (37 citations)
- Why Are Deep Representations Good Perceptual Quality Features? (23 citations)
- Controllable Image Synthesis via SegVAE (22 citations)
- ALRe: Outlier Detection for Guided Refinement (2 citations)
Text-to-image diffusion · 7 papers
- GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images (139 citations)
- CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis (81 citations)
- RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval (36 citations)
- Structure-Aware Generation Network for Recipe Generation from Images (36 citations)
- Visual-Relation Conscious Image Generation from Structured-Text (22 citations)
- Modeling Artistic Workflows for Image Generation and Editing (21 citations)
- Conditional Image Repainting via Semantic Bridge and Piecewise Value Function (5 citations)
