mlsanityData to 14 Oct 2026

Detail-revealing Deep Video Super-resolution

arXiv 1704.02738 ↗First posted 10 Apr 2017cs.CVcited by 148

Not on the map. Why?

Cited by 31 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Previous CNN-based video super-resolution approaches need to align multiple frames to the reference. In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results. We accordingly propose a `sub-pixel motion compensation' (SPMC) layer in a CNN framework. Analysis and experiments show the suitability of this layer in video SR. The final end-to-end, scalable CNN framework effectively incorporates the SPMC layer and fuses multiple frames to reveal image details. Our implementation can generate visually and quantitatively high-quality results, superior to current state-of-the-arts, without the need of parameter tuning.

Key facts. Cited by 148 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 31; 2022: 35; 2023: 19; 2024: 12; 2025: 32; 2026: 19.

148 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. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 170
  4. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  5. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 132
  6. 2021Video Super-Resolution Transformercited by 121
  7. 2022Generating Long Videos of Dynamic Scenescited by 113
  8. 2022VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolutioncited by 101
  9. 2022Rethinking Alignment in Video Super-Resolution Transformerscited by 71
  10. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  11. 2021Encoding physics to learn reaction-diffusion processescited by 61
  12. 2022Learning Trajectory-Aware Transformer for Video Super-Resolutioncited by 61
38 more
  1. 2023Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutioncited by 59
  2. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 50
  3. 2022RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolutioncited by 44
  4. 2023Frame-Event Alignment and Fusion Network for High Frame Rate Trackingcited by 43
  5. 2024DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Modelscited by 34
  6. 2025DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolutioncited by 31
  7. 2021Omniscient Video Super-Resolutioncited by 30
  8. 2024VideoGigaGAN: Towards Detail-rich Video Super-Resolutioncited by 30
  9. 2024Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attentioncited by 29
  10. 2024FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurringcited by 28
  11. 2022Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolutioncited by 25
  12. 2021A Comprehensive Review of Deep Learning-based Single Image Super-resolutioncited by 23
  13. 2023Can SAM Boost Video Super-Resolution?cited by 21
  14. 2022Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modelingcited by 20
  15. 2022NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Resultscited by 20
  16. 2022AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Resultscited by 20
  17. 2022Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-Resolutioncited by 20
  18. 2021FDAN: Flow-guided Deformable Alignment Network for Video Super-Resolutioncited by 19
  19. 2021Self-Conditioned Probabilistic Learning of Video Rescalingcited by 19
  20. 2023Local-Global Temporal Difference Learning for Satellite Video Super-Resolutioncited by 19
  21. 2021Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurringcited by 17
  22. 2021Memory-Augmented Non-Local Attention for Video Super-Resolutioncited by 17
  23. 2023AnyFlow: Arbitrary Scale Optical Flow with Implicit Neural Representationcited by 17
  24. 2025PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancementcited by 17
  25. 2022Temporal Consistency Learning of inter-frames for Video Super-Resolutioncited by 16
  26. 2021NTIRE 2021 Challenge on Video Super-Resolutioncited by 15
  27. 2022Self-Supervised Deep Blind Video Super-Resolutioncited by 15
  28. 2025One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolutioncited by 15
  29. 2022Structured Sparsity Learning for Efficient Video Super-Resolutioncited by 14
  30. 2025UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Spacecited by 14
  31. 2022Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learningcited by 12
  32. 2024LAVIB: A Large-scale Video Interpolation Benchmarkcited by 11
  33. 2022Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolutioncited by 10
  34. 2022Towards Interpretable Video Super-Resolution via Alternating Optimizationcited by 10
  35. 2025Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restorationcited by 10
  36. 2021Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsamplingcited by 9
  37. 2021Efficient Space-time Video Super Resolution using Low-Resolution Flow and Mask Upsamplingcited by 9
  38. 2021EDPN: Enhanced Deep Pyramid Network for Blurry Image Restorationcited by 9

50 most cited of 148 All 148 (JSON)