Paper with Code --- [CVPR2021]
Transformer for CV
- Pre-Trained Image Processing Transformer, [Paper], [Code]
- Transformer Interpretability Beyond Attention Visualization, [Paper], [Code]
- Generative Adversarial Transformers, [Paper], [Code]
- Transformer in Transfomer, [Paper], [Code]
- End-to-End Video Instance Segmentation with Transformers, [Paper]
- Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers, [Paper], [Code]
- Pose Recognition with Cascade Transformers, [Paper], [Code]
- CoaT: Co-Scale Conv-Attentional Image Transformers, [Paper], [Code]
- LocalViT: Bringing Locality to Vision Transformers, [Paper], [Code]
- HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers, [Code]
Image Manipulation
- AdderSR: Towards Energy Efficient Image Super-Resolution,
Efficient SR, [Paper], [Code] - Exploring Sparsity in Image Super-Resolution for Efficient Inference,
Efficient SR, [Paper], [Code] - ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic,
Efficient SR, [Paper], [Code] - Data-Free Knowledge Distillation For Image Super-Resolution,
Efficient SR - Cross-MPI: Cross-scale Stereo for Image Super-Resolution using Multiplane Images,
Stereo SR, [Paper], [Code] - Learning Continuous Image Representation with Local Implicit Image Function,
SR with Large Scale Factor,Oral, [Paper], [Code] - GLEAN: Generative LatEnt BANk for Large-Factor Image Super-Resolution,
SR with Large Scale Factor,Oral, [Paper], [Code] - SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation,
Arbitrary Transformation, [Paper], [Code] - LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution,
Omnidirectional Image Super-resolution, [Code] - Unsupervised Degradation Representation Learning for Blind Super-Resolution,
Blins SR, [Paper], [Code] - Flow-based Kernel Prior with Application to Blind Super-Resolution,
Blind SR, [Paper], [Code] - KOALAnet: Blind Super-Resolution Using Kernel-Oriented Adaptive Local Adjustment,
Blind SR, [Paper] - Learning the Non-Differentiable Optimization for Blind Super-Resolution
- Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation
- DeFlow: Learning Complex Image Degradations From Unpaired Data With Conditional Flows,
Real/Domain SR, [Paper] - Towards Real-World Blind Face Restoration with Generative Facial Prior,
Blind Face Restoration, [Paper], [Project] - GAN Prior Embedded Network for Blind Face Restoration in the Wild,
Blind Face Restoration, [Paper], [Code] - MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution,
Reference SR, [Paper], [Code] - Deep Burst Super-Resolution,
Burst SR, [Paper], [Project] - Interpreting Super-Resolution Networks With Local Attribution Maps,
Interpreting SR, [Paper], [Project] - Fast Bayesian Uncertainty Estimation and Reduction of Batch Normalized Single Image Super-Resolution Network,
Bayesian, [Paper], [Code] - Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images,
Image Denoising, [Paper] - NBNet: Noise Basis Learning for Image Denoising with Subspace Projection,
Image Denoising, [Paper] - Deep Convolutional Dictionary Learning for Image Denoising,
Image Denoising, [Paper], [Code] - Multi-Stage Progressive Image Restoration,
Image Restoration, [Papper], [Code] - Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration,
Image Restoration, [Paper], [Code] - Auto-Exposure Fusion for Single-Image Shadow Removal,
Shadow Removal, [Paper], [Code] - Robust Reflection Removal with Reflection-free Flash-only Cues,
Shadow Removal, [Paper], [Code] - Removing Raindrops and Rain Streaks in One Go,
Image Deraining, - From Rain Generation to Rain Removal,
Image Deraining, [Paper] - Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation,
Image Deraining, [Code] - DeFMO: Deblurring and Shape Recovery of Fast Moving Objects,
Image Deblurring, [Paper], [Code] - Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes,
Image Deblurring, [Code] - Contrastive Learning for Compact Single Image Dehazing,
Image Dehazing, [Code] - PD-GAN:Probabilistic Diverse GAN for Image Inpainting,
Image Inpainting, [Paper], [Code] - Generating Diverse Structure for Image Inpainting with Hierarchical VQ-VAE,
Image Inpainting, [Paper], [Code] - Invertible Image Signal Processing,
ISP,RAW2RGB, [Paper], [Code] - Progressive Semantic-Aware Style Transformation for Blind Face Restoration,
Blind Face Restoration, [Paper], [Code] - HiSD: Image-to-image Translation via Hierarchical Style Disentanglement,
Image Translation, [Paper], [Code] - Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation,
Image Translation, [Paper][Code] - Spatially-Adaptive Pixelwise Networks for Fast Image Translation,
Image Translation, [Paper][Code] - CoMoGAN: continuous model-guided image-to-image translation,
Image Translation,Oral, [Paper], [Code] - Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing,
Image Editing, [Paper], [Code] - Anycost GANs for Interactive Image Synthesis and Editing,
Image Editing, [Paper], [Code] - PISE: Person Image Synthesis and Editing with Decoupled GAN,
Image Editing, [Paper], [Code] - Closed-Form Factorization of Latent Semantics in GANs,
Image Editing, [Paper], [Code] - StyleMapGAN: Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing,
Image Editing, [Paper], [Code] - Learning Multi-Scale Photo Exposure Correction,
Image Enhancement, [Paper], [Code] - Restoring Extremely Dark Images in Real Time,
Image Enhancement,RAW2RGB, [Code]
Video Manipulation
- FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation,
Video Interpolation, [Paper], [Code] - CDFI: Compression-driven Network Design for Frame Interpolation,
Video Interpolation, [Paper], [Code] - Deep Animation Video Interpolation in the Wild,
Video Interpolation, [Paper], [Code] - Time Lens: Event-Based Video Frame Interpolation,
Video Interpolation, [Paper], [Project] - Temporal Modulation Network for Controllable Space-Time Video Super-Resolution,
Video Super-Resolution, [Code], [Paper] - BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond,
Video Super-Resolution, [Paper], [Code] - Space-Time Distillation for Video Super-Resolution,
Video Super-Resolution, [Paper] - Video Rescaling Networks with Joint Optimization Strategies for Downscaling and Upscaling,
Video Rescaling, [Project], [Code] - Efficient Multi-Stage Video Denoising with Recurrent Spatio-Temporal Fusion,
Video Denoising, [Paper] - ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring,
Video Deblurring, [Paper], [Code] - Gated Spatio-Temporal Attention-Guided Video Deblurring,
Video Deblurring - Real-Time High Resolution Background Matting,
Video Background Matting, [Paper], [Code] - Deep Video Matting via Spatio-Temporal Alignment and Aggregation,
Video Matting, [Paper] - Learning to Restore Hazy Video: A New Real-World Dataset and A New Method,
Video Dehazing, - Semi-Supervised Video Deraining with Dynamic Rain Generator,
Video Deraining, [Paper], [Code] - Self-Aligned Video Deraining With Transmission-Depth Consistency,
- Restore From Restored: Video Restoration With Pseudo Clean Video,
Video Restoration, [Paper] - Learning Temporal Consistency for Low Light Video Enhancement From Single Images,
Low-light Video Enhancement, - Progressive Temporal Feature Alignment Network for Video Inpainting,
Video Inpainting, [Paper], [Code] - Learning by Aligning Videos in Time,
Video Alignment, [Paper] - Skip-Convolutions for Efficient Video Processing,
High-Level Video Tasks, [Paper] - Spatio-Temporal Contrastive Video Representation Learning,
Contrastive Video Representation Learning, [Paper] - Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency, ``
- Real-Time Selfie Video Stabilization,
Video Stabilization, [Paper]
Optical Flow
- AutoFlow: Learning a Better Training Set for Optical Flow,
Oral, [Paper], [Code] - UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning,
self-guided module, [Paper] - Learning Optical Flow From Still Images,
introduce a framework to generate accurate ground-truth optical flow annotations, [Paper], [Code]