CVPR 2016 accepted papers on Image generation
40 of the 643 papers accepted at CVPR 2016 (6.2%) are on Image generation. They fall into 5 topics.
See CVPR 2016 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 · 24 papers
- Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (2,321 citations)
- Non-Local Image Dehazing (1,680 citations)
- Rain Streak Removal Using Layer Priors (1,002 citations)
- Blind Image Deblurring Using Dark Channel Prior (825 citations)
- ReconNet: Non-Iterative Reconstruction of Images From Compressively Sensed Measurements (743 citations)
- A Comparative Study for Single Image Blind Deblurring (464 citations)
- Composition-Preserving Deep Photo Aesthetics Assessment (291 citations)
- A Holistic Approach to Cross-Channel Image Noise Modeling and Its Application to Image Denoising (290 citations)
- Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization (264 citations)
- Automatic Image Cropping : A Computational Complexity Study (124 citations)
- Joint Recovery of Dense Correspondence and Cosegmentation in Two Images (121 citations)
- Robust Kernel Estimation With Outliers Handling for Image Deblurring (113 citations)
and 12 more in the interactive map.
Autoregressive and latent generation · 8 papers
- Deep Supervised Hashing for Fast Image Retrieval (944 citations)
- Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis (718 citations)
- Visualizing and Understanding Deep Texture Representations (141 citations)
- Group MAD Competition - A New Methodology to Compare Objective Image Quality Models (98 citations)
- Comparative Deep Learning of Hybrid Representations for Image Recommendations (70 citations)
- Laplacian Patch-Based Image Synthesis (45 citations)
- Progressive Feature Matching With Alternate Descriptor Selection and Correspondence Enrichment (21 citations)
- Using Spatial Order to Boost the Elimination of Incorrect Feature Matches (3 citations)
Editing and style transfer · 3 papers
- Image Style Transfer Using Convolutional Neural Networks (6,164 citations)
- Split and Match: Example-Based Adaptive Patch Sampling for Unsupervised Style Transfer (132 citations)
- Automatic Content-Aware Color and Tone Stylization (63 citations)
Super-resolution · 3 papers
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (7,310 citations)
- Deeply-Recursive Convolutional Network for Image Super-Resolution (3,131 citations)
- Seven Ways to Improve Example-Based Single Image Super Resolution (487 citations)
Text-to-image diffusion · 2 papers
- Learning Deep Structure-Preserving Image-Text Embeddings (814 citations)
- Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation (357 citations)
