mlsanityData to 14 Oct 2026

EDVR: Video Restoration with Enhanced Deformable Convolutional Networks

arXiv 1905.02716 ↗First posted 7 May 2019cs.CVcited by 494

Not on the map. Why?

Cited by 45 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Video restoration tasks, including super-resolution, deblurring, etc, are drawing increasing attention in the computer vision community. A challenging benchmark named REDS is released in the NTIRE19 Challenge. This new benchmark challenges existing methods from two aspects: (1) how to align multiple frames given large motions, and (2) how to effectively fuse different frames with diverse motion and blur. In this work, we propose a novel Video Restoration framework with Enhanced Deformable networks, termed EDVR, to address these challenges. First, to handle large motions, we devise a Pyramid, Cascading and Deformable (PCD) alignment module, in which frame alignment is done at the feature level using deformable convolutions in a coarse-to-fine manner. Second, we propose a Temporal and Spatial Attention (TSA) fusion module, in which attention is applied both temporally and spatially, so as to emphasize important features for subsequent restoration. Thanks to these modules, our EDVR wins the champions and outperforms the second place by a large margin in all four tracks in the NTIRE19 video restoration and enhancement challenges. EDVR also demonstrates superior performance to state-of-the-art published methods on video super-resolution and deblurring. The code is available at https://github.com/xinntao/EDVR.

Key facts. Cited by 494 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 87; 2022: 118; 2023: 87; 2024: 69; 2025: 82; 2026: 51.

494 papers.

Sort:

By area:

  1. 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 342
  2. 2022VRT: A Video Restoration Transformercited by 220
  3. 2022VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolutioncited by 176
  4. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 170
  5. 2023Neural Video Compression with Diverse Contextscited by 165
  6. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 153
  7. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  8. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 134
  9. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 132
  10. 2021XVFI: eXtreme Video Frame Interpolationcited by 126
  11. 2021Video Super-Resolution Transformercited by 121
  12. 2022Towards An End-to-End Framework for Flow-Guided Video Inpaintingcited by 113
38 more
  1. 2022VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolutioncited by 101
  2. 2022Deep Image Deblurring: A Surveycited by 94
  3. 2021FaPN: Feature-aligned Pyramid Network for Dense Image Predictioncited by 81
  4. 2022Changer: Feature Interaction is What You Need for Change Detectioncited by 79
  5. 2022Rethinking Alignment in Video Super-Resolution Transformerscited by 71
  6. 2021Robust Reference-based Super-Resolution via C2-Matchingcited by 69
  7. 2022A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shiftcited by 68
  8. 2021Burst Image Restoration and Enhancementcited by 64
  9. 2024VEnhancer: Generative Space-Time Enhancement for Video Generationcited by 64
  10. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  11. 2021Improving Image Restoration by Revisiting Global Information Aggregationcited by 61
  12. 2022Learning Trajectory-Aware Transformer for Video Super-Resolutioncited by 61
  13. 2023Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutioncited by 59
  14. 2021Explore Image Deblurring via Blur Kernel Spacecited by 58
  15. 2021HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantizationcited by 58
  16. 2022Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Networkcited by 57
  17. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
  18. 2022Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Predictioncited by 55
  19. 2021MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motionscited by 54
  20. 2021ARVo: Learning All-Range Volumetric Correspondence for Video Deblurringcited by 54
  21. 2021Temporal Modulation Network for Controllable Space-Time Video Super-Resolutioncited by 54
  22. 2021ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imagingcited by 51
  23. 2022Reference-based Image Super-Resolution with Deformable Attention Transformercited by 51
  24. 2021NTIRE 2021 Challenge on Image Deblurringcited by 50
  25. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 50
  26. 2023Implicit Temporal Modeling with Learnable Alignment for Video Recognitioncited by 46
  27. 2021HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Datasetcited by 45
  28. 2022RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolutioncited by 44
  29. 2022Flow-Guided Sparse Transformer for Video Deblurringcited by 43
  30. 2023Frame-Event Alignment and Fusion Network for High Frame Rate Trackingcited by 43
  31. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 43
  32. 2021Deep Video Matting via Spatio-Temporal Alignment and Aggregationcited by 41
  33. 2021Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumescited by 41
  34. 2022Multi-Bracket High Dynamic Range Imaging with Event Camerascited by 37
  35. 2021NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Resultscited by 36
  36. 2023Enhancing Video Super-Resolution via Implicit Resampling-based Alignmentcited by 35
  37. 2024DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Modelscited by 34
  38. 2022Low-Light Video Enhancement with Synthetic Event Guidancecited by 33

50 most cited of 494 All 494 (JSON)