CVPR 2017 accepted papers on Image generation
70 of the 783 papers accepted at CVPR 2017 (8.9%) are on Image generation, compared with 6.2% at CVPR 2016. They fall into 5 topics.
See CVPR 2017 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 · 26 papers
- Learning Deep CNN Denoiser Prior for Image Restoration (2,114 citations)
- Removing Rain From Single Images via a Deep Detail Network (1,298 citations)
- Benchmarking Denoising Algorithms With Real Photographs (689 citations)
- From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur (466 citations)
- Non-Local Color Image Denoising With Convolutional Neural Networks (387 citations)
- Image Deblurring via Extreme Channels Prior (378 citations)
- Hyper-Laplacian Regularized Unidirectional Low-Rank Tensor Recovery for Multispectral Image Denoising (224 citations)
- Fast Haze Removal for Nighttime Image Using Maximum Reflectance Prior (206 citations)
- Learning Fully Convolutional Networks for Iterative Non-Blind Deconvolution (200 citations)
- Hallucinating Very Low-Resolution Unaligned and Noisy Face Images by Transformative Discriminative Autoencoders (164 citations)
- Single Image Reflection Suppression (156 citations)
- A Unified Approach of Multi-Scale Deep and Hand-Crafted Features for Defocus Estimation (127 citations)
and 14 more in the interactive map.
Autoregressive and latent generation · 19 papers
- Semantic Image Inpainting With Deep Generative Models (1,226 citations)
- High-Resolution Image Inpainting Using Multi-Scale Neural Patch Synthesis (921 citations)
- Scribbler: Controlling Deep Image Synthesis With Sketch and Color (535 citations)
- Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space (504 citations)
- Deep Image Matting (478 citations)
- Comparative Evaluation of Hand-Crafted and Learned Local Features (321 citations)
- Deep Feature Interpolation for Image Content Changes (319 citations)
- Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval (285 citations)
- Deep Learning of Human Visual Sensitivity in Image Quality Assessment Framework (278 citations)
- Diversified Texture Synthesis With Feed-Forward Networks (276 citations)
- A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessment (241 citations)
- Learning Diverse Image Colorization (202 citations)
and 7 more in the interactive map.
Editing and style transfer · 13 papers
- Image-To-Image Translation With Conditional Adversarial Networks (22,687 citations)
- Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis (873 citations)
- Deep Photo Style Transfer (692 citations)
- Generative Face Completion (619 citations)
- Controlling Perceptual Factors in Neural Style Transfer (520 citations)
- StyleBank: An Explicit Representation for Neural Image Style Transfer (491 citations)
- Neural Face Editing With Intrinsic Image Disentangling (307 citations)
- StyleNet: Generating Attractive Visual Captions With Styles (306 citations)
- Learning Residual Images for Face Attribute Manipulation (289 citations)
- Deep Image Harmonization (257 citations)
- Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer (182 citations)
- Synthesizing Normalized Faces From Facial Identity Features (149 citations)
and 1 more in the interactive map.
GANs · 6 papers
- Learning From Simulated and Unsupervised Images Through Adversarial Training (1,971 citations)
- Age Progression/Regression by Conditional Adversarial Autoencoder (1,124 citations)
- Disentangled Representation Learning GAN for Pose-Invariant Face Recognition (1,090 citations)
- Stacked Generative Adversarial Networks (432 citations)
- DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data (286 citations)
- Generative Attribute Controller With Conditional Filtered Generative Adversarial Networks (97 citations)
Super-resolution · 6 papers
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (12,597 citations)
- Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (3,099 citations)
- Image Super-Resolution via Deep Recursive Residual Network (2,511 citations)
- Hyperspectral Image Super-Resolution via Non-Local Sparse Tensor Factorization (341 citations)
- Attention-Aware Face Hallucination via Deep Reinforcement Learning (240 citations)
- Simultaneous Super-Resolution and Cross-Modality Synthesis of 3D Medical Images Using Weakly-Supervised Joint Convolutional Sparse Coding (216 citations)
