mlsanityData to 7 Oct 2026

BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment

arXiv 2104.13371 ↗First posted 27 Apr 2021cs.CVcited by 340

Not on the map. Why?

Cited by 56 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A recurrent structure is a popular framework choice for the task of video super-resolution. The state-of-the-art method BasicVSR adopts bidirectional propagation with feature alignment to effectively exploit information from the entire input video. In this study, we redesign BasicVSR by proposing second-order grid propagation and flow-guided deformable alignment. We show that by empowering the recurrent framework with the enhanced propagation and alignment, one can exploit spatiotemporal information across misaligned video frames more effectively. The new components lead to an improved performance under a similar computational constraint. In particular, our model BasicVSR++ surpasses BasicVSR by 0.82 dB in PSNR with similar number of parameters. In addition to video super-resolution, BasicVSR++ generalizes well to other video restoration tasks such as compressed video enhancement. In NTIRE 2021, BasicVSR++ obtains three champions and one runner-up in the Video Super-Resolution and Compressed Video Enhancement Challenges. Codes and models will be released to MMEditing.

Key facts. Cited by 340 papers in the map (data through 7 Oct 2026). Builds on 31 of its 47 references that are in the map. First posted on arXiv 27 Apr 2021.

Builds on

31 of 47 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2017Deformable Convolutional Networkscited by 1,481
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  5. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  6. 2017Video Enhancement with Task-Oriented Flowcited by 612
  7. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  8. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  9. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
  10. 2020BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyondcited by 303
  11. 2020Softmax Splatting for Video Frame Interpolationcited by 276
  12. 2018TDAN: Temporally Deformable Alignment Network for Video Super-Resolutioncited by 225
19 more
  1. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  2. 2018Frame-Recurrent Video Super-Resolutioncited by 160
  3. 2016Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensationcited by 156
  4. 2017Detail-revealing Deep Video Super-resolutioncited by 147
  5. 2019Recurrent Back-Projection Network for Video Super-Resolutioncited by 147
  6. 2020Video Super-Resolution with Recurrent Structure-Detail Networkcited by 116
  7. 2019Spatio-Temporal Filter Adaptive Network for Video Deblurringcited by 106
  8. 2020Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolutioncited by 91
  9. 2020MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolutioncited by 89
  10. 2020Video Super-resolution with Temporal Group Attentioncited by 81
  11. 2020Understanding Deformable Alignment in Video Super-Resolutioncited by 78
  12. 2019Efficient Video Super-Resolution through Recurrent Latent Space Propagationcited by 69
  13. 2017Residual Conv-Deconv Grid Network for Semantic Segmentationcited by 57
  14. 2020Revisiting Temporal Modeling for Video Super-resolutioncited by 46
  15. 2018Sparse Attentive Backtracking: Temporal CreditAssignment Through Remindingcited by 33
  16. 2021NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Resultscited by 26
  17. 2018Optimizing Video Object Detection via a Scale-Time Latticecited by 25
  18. 2016Higher Order Recurrent Neural Networkscited by 11
  19. 2021Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoisingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 58; 2023: 68; 2024: 62; 2025: 90; 2026: 58.

340 papers.

Sort:

By area:

  1. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Modelscited by 349
  2. 2022VRT: A Video Restoration Transformercited by 219
  3. 2023ProPainter: Improving Propagation and Transformer for Video Inpaintingcited by 193
  4. 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolationcited by 177
  5. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  6. 2023Neural Video Compression with Diverse Contextscited by 155
  7. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133
  8. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
  9. 2022Towards An End-to-End Framework for Flow-Guided Video Inpaintingcited by 111
  10. 2023VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimationcited by 82
  11. 2022Rethinking Alignment in Video Super-Resolution Transformerscited by 71
  12. 2022A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shiftcited by 68
38 more
  1. 2024VEnhancer: Generative Space-Time Enhancement for Video Generationcited by 64
  2. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  3. 2023Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutioncited by 59
  4. 2024RainMamba: Enhanced Locality Learning with State Space Models for Video Derainingcited by 56
  5. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
  6. 2022Reference-based Image Super-Resolution with Deformable Attention Transformercited by 50
  7. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  8. 2023Implicit Temporal Modeling with Learnable Alignment for Video Recognitioncited by 44
  9. 2022Flow-Guided Sparse Transformer for Video Deblurringcited by 43
  10. 2023High-Fidelity and Freely Controllable Talking Head Video Generationcited by 42
  11. 2023DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Modelscited by 41
  12. 2023MGMAE: Motion Guided Masking for Video Masked Autoencodingcited by 40
  13. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 40
  14. 2024KVQ: Kwai Video Quality Assessment for Short-form Videoscited by 38
  15. 2023Enhancing Video Super-Resolution via Implicit Resampling-based Alignmentcited by 35
  16. 2023Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolutioncited by 33
  17. 2024DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Modelscited by 33
  18. 2024RealViformer: Investigating Attention for Real-World Video Super-Resolutioncited by 33
  19. 2022BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignmentcited by 32
  20. 2022Imaging through the Atmosphere using Turbulence Mitigation Transformercited by 31
  21. 2024VideoGigaGAN: Towards Detail-rich Video Super-Resolutioncited by 30
  22. 2025DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolutioncited by 30
  23. 2022Mitigating Artifacts in Real-World Video Super-Resolution Modelscited by 29
  24. 2023NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXercited by 29
  25. 2024Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attentioncited by 29
  26. 2024FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurringcited by 28
  27. 2022Learning Motion-Robust Remote Photoplethysmography through Arbitrary Resolution Videoscited by 26
  28. 2023OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformercited by 26
  29. 2023Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfercited by 25
  30. 2021Revisiting Temporal Alignment for Video Restorationcited by 24
  31. 2022Video Demoireing with Relation-Based Temporal Consistencycited by 24
  32. 2022Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-ahead Forward Onescited by 24
  33. 2025MatAnyone: Stable Video Matting with Consistent Memory Propagationcited by 24
  34. 2022Neural Compression-Based Feature Learning for Video Restorationcited by 23
  35. 2022AnimeSR: Learning Real-World Super-Resolution Models for Animation Videoscited by 23
  36. 2022CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streamingcited by 23
  37. 2024Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolutioncited by 23
  38. 2023Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Priorcited by 22

50 most cited of 340 All 340 (JSON)