TPAMI 2021 papers on Image generation
46 of the 516 papers published in TPAMI 2021 (8.9%) are on Image generation, compared with 10.9% at TPAMI 2020. They fall into 6 topics.
See TPAMI 2021 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 · 22 papers
- Plug-and-Play Image Restoration With Deep Denoiser Prior (1,245 citations)
- Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation (806 citations)
- Deep Learning-based Multi-focus Image Fusion: A Survey and A Comparative Study (217 citations)
- Learning End-to-End Lossy Image Compression: A Benchmark (195 citations)
- Physics-based Noise Modeling for Extreme Low-light Photography (141 citations)
- Path-Restore: Learning Network Path Selection for Image Restoration (121 citations)
- DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring (105 citations)
- Coded Hyperspectral Image Reconstruction using Deep External and Internal Learning (104 citations)
- Reversible Data Hiding By Using CNN Prediction and Adaptive Embedding (103 citations)
- Learning Frequency Domain Priors for Image Demoireing (91 citations)
- Physics-Based Shadow Image Decomposition for Shadow Removal (89 citations)
- Enhancement-Registration-Homogenization (ERH): A Comprehensive Underwater Visual Reconstruction Paradigm (68 citations)
and 10 more in the interactive map.
Super-resolution · 7 papers
- Structure-Preserving Image Super-Resolution (136 citations)
- RankSRGAN: Super Resolution Generative Adversarial Networks With Learning to Rank (76 citations)
- Deep Spatial-Angular Regularization for Light Field Imaging, Denoising, and Super-Resolution (70 citations)
- Toward Real-World Super-Resolution via Adaptive Downsampling Models (48 citations)
- E2SRI: Learning to Super-Resolve Intensity Images From Events (30 citations)
- Joint Framework for Single Image Reconstruction and Super-Resolution With an Event Camera (22 citations)
- The Conditional Super Learner (8 citations)
Editing and style transfer · 7 papers
- DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition (144 citations)
- PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal (47 citations)
- Shape-Matching GAN++: Scale Controllable Dynamic Artistic Text Style Transfer (29 citations)
- Progressive and Aligned Pose Attention Transfer for Person Image Generation (24 citations)
- Recursive Copy and Paste GAN: Face Hallucination from Shaded Thumbnails (23 citations)
- Text-Guided Human Image Manipulation via Image-Text Shared Space (17 citations)
- Non-Local Representation Based Mutual Affine-Transfer Network for Photorealistic Stylization (8 citations)
GANs · 5 papers
- Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models (847 citations)
- SymReg-GAN: Symmetric Image Registration with Generative Adversarial Networks (84 citations)
- Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis (83 citations)
- AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks (60 citations)
- iFlowGAN: An Invertible Flow-based Generative Adversarial Network For Unsupervised Image-to-Image Translation (19 citations)
Autoregressive and latent generation · 4 papers
- Efficient Semantic Image Synthesis via Class-Adaptive Normalization (96 citations)
- Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment (35 citations)
- Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning (22 citations)
- Learning Asymmetric and Local Features in Multi-Dimensional Data Through Wavelets With Recursive Partitioning (6 citations)
