CVPR 2020 accepted papers on Image generation
167 of the 1,467 papers accepted at CVPR 2020 (11.4%) are on Image generation, compared with 10.9% at CVPR 2019. They fall into 7 topics.
See CVPR 2020 in the interactive map
Submitting to CVPR? 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 · 51 papers
- Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement (2,412 citations)
- Multi-Scale Boosted Dehazing Network With Dense Feature Fusion (1,103 citations)
- Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network (840 citations)
- From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (645 citations)
- Domain Adaptation for Image Dehazing (475 citations)
- A Model-Driven Deep Neural Network for Single Image Rain Removal (453 citations)
- Deblurring by Realistic Blurring (450 citations)
- Learning to Restore Low-Light Images via Decomposition-and-Enhancement (448 citations)
- Self2Self With Dropout: Learning Self-Supervised Denoising From Single Image (437 citations)
- CycleISP: Real Image Restoration via Improved Data Synthesis (398 citations)
- Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting (388 citations)
- All in One Bad Weather Removal Using Architectural Search (360 citations)
and 39 more in the interactive map.
Editing and style transfer · 38 papers
- StarGAN v2: Diverse Image Synthesis for Multiple Domains (1,665 citations)
- Face X-Ray for More General Face Forgery Detection (1,140 citations)
- MaskGAN: Towards Diverse and Interactive Facial Image Manipulation (1,085 citations)
- Image2StyleGAN++: How to Edit the Embedded Images? (518 citations)
- SEAN: Image Synthesis With Semantic Region-Adaptive Normalization (350 citations)
- Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning (336 citations)
- ManiGAN: Text-Guided Image Manipulation (283 citations)
- Editing in Style: Uncovering the Local Semantics of GANs (271 citations)
- Controllable Person Image Synthesis With Attribute-Decomposed GAN (269 citations)
- Cross-Domain Correspondence Learning for Exemplar-Based Image Translation (262 citations)
- Deep Image Spatial Transformation for Person Image Generation (216 citations)
- Reference-Based Sketch Image Colorization Using Augmented-Self Reference and Dense Semantic Correspondence (175 citations)
and 26 more in the interactive map.
Autoregressive and latent generation · 27 papers
- CNN-Generated Images Are Surprisingly Easy to Spot... for Now (1,121 citations)
- MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment (432 citations)
- From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality (397 citations)
- Perceptual Quality Assessment of Smartphone Photography (372 citations)
- DoveNet: Deep Image Harmonization via Domain Verification (213 citations)
- UCTGAN: Diverse Image Inpainting Based on Unsupervised Cross-Space Translation (208 citations)
- Attention-Guided Hierarchical Structure Aggregation for Image Matting (182 citations)
- Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation (167 citations)
- SketchyCOCO: Image Generation From Freehand Scene Sketches (143 citations)
- Tangent Images for Mitigating Spherical Distortion (141 citations)
- Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis (111 citations)
- Prior Guided GAN Based Semantic Inpainting (102 citations)
and 15 more in the interactive map.
Super-resolution · 23 papers
- Learning Texture Transformer Network for Image Super-Resolution (970 citations)
- Deep Unfolding Network for Image Super-Resolution (653 citations)
- Residual Feature Aggregation Network for Image Super-Resolution (630 citations)
- PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models (541 citations)
- Structure-Preserving Super Resolution With Gradient Guidance (404 citations)
- Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining (398 citations)
- Closed-Loop Matters: Dual Regression Networks for Single Image Super-Resolution (350 citations)
- Meta-Transfer Learning for Zero-Shot Super-Resolution (316 citations)
- Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and Landmark Estimation (198 citations)
- Unpaired Image Super-Resolution Using Pseudo-Supervision (190 citations)
- Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy (162 citations)
- Unified Dynamic Convolutional Network for Super-Resolution With Variational Degradations (147 citations)
and 11 more in the interactive map.
GANs · 20 papers
- Analyzing and Improving the Image Quality of StyleGAN (6,132 citations)
- Interpreting the Latent Space of GANs for Semantic Face Editing (1,035 citations)
- Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions (456 citations)
- Global Texture Enhancement for Fake Face Detection in the Wild (371 citations)
- A U-Net Based Discriminator for Generative Adversarial Networks (350 citations)
- Image Processing Using Multi-Code GAN Prior (323 citations)
- Adversarial Latent Autoencoders (249 citations)
- Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation (247 citations)
- MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks (245 citations)
- CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks (220 citations)
- GAN Compression: Efficient Architectures for Interactive Conditional GANs (210 citations)
- Cascade EF-GAN: Progressive Facial Expression Editing With Local Focuses (119 citations)
and 8 more in the interactive map.
Text-to-image diffusion · 6 papers
- RiFeGAN: Rich Feature Generation for Text-to-Image Synthesis From Prior Knowledge (116 citations)
- Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition (113 citations)
- STEFANN: Scene Text Editor Using Font Adaptive Neural Network (77 citations)
- CookGAN: Causality Based Text-to-Image Synthesis (76 citations)
- SwapText: Image Based Texts Transfer in Scenes (75 citations)
- UnrealText: Synthesizing Realistic Scene Text Images From the Unreal World (49 citations)
Fast diffusion sampling · 2 papers
- Pattern-Structure Diffusion for Multi-Task Learning (93 citations)
- Normalizing Flows With Multi-Scale Autoregressive Priors (11 citations)
