mlsanityData to 7 Oct 2026

Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors

arXiv 2407.09919 ↗First posted 13 Jul 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding spatial detail reproduction, temporal consistency, and computational complexity. In this paper, we first describe a strong baseline for AVSR by putting together three variants of elementary building blocks: 1) a flow-guided recurrent unit that aggregates spatiotemporal information from previous frames, 2) a flow-refined cross-attention unit that selects spatiotemporal information from future frames, and 3) a hyper-upsampling unit that generates scaleaware and content-independent upsampling kernels. We then introduce ST-AVSR by equipping our baseline with a multi-scale structural and textural prior computed from the pre-trained VGG network. This prior has proven effective in discriminating structure and texture across different locations and scales, which is beneficial for AVSR. Comprehensive experiments show that ST-AVSR significantly improves super-resolution quality, generalization ability, and inference speed over the state-of-theart. The code is available at https://github.com/shangwei5/ST-AVSR.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 13 Jul 2024.

Builds on

39 of 61 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  6. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  7. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  8. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  9. 2017Deep Image Priorcited by 1,097
  10. 2016HyperNetworkscited by 1,003
  11. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  12. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
27 more
  1. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  2. 2020Convolutional Occupancy Networkscited by 760
  3. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  4. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  5. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  6. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  7. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  8. 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 340
  9. 2020BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyondcited by 303
  10. 2019Meta-SR: A Magnification-Arbitrary Network for Super-Resolutioncited by 180
  11. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  12. 2016Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensationcited by 156
  13. 2017Detail-revealing Deep Video Super-resolutioncited by 147
  14. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133
  15. 2021Local Texture Estimator for Implicit Representation Functioncited by 126
  16. 2022VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolutioncited by 101
  17. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 69
  18. 2020Learning A Single Network for Scale-Arbitrary Super-Resolutioncited by 65
  19. 2023Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolutioncited by 51
  20. 2014Sparse Modeling for Image and Vision Processingcited by 48
  21. 2021Locally Adaptive Structure and Texture Similarity for Image Quality Assessmentcited by 32
  22. 2023OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolutioncited by 17
  23. 2023Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Timecited by 16
  24. 2023MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolutioncited by 16
  25. 2020OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Networkcited by 15
  26. 2023LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolutioncited by 12
  27. 2022CUF: Continuous Upsampling Filterscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 3.

9 papers.

  1. 2025Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modelingcited by 47
  2. 2025Arbitrary-Scale 3D Gaussian Super-Resolutioncited by 5
  3. 2025StereoINR: Cross-View Geometry Consistent Stereo Super Resolution with Implicit Neural Representationcited by 3
  4. 2025Continuous Space-Time Video Super-Resolution with 3D Fourier Fieldscited by 3
  5. 2026Vanilla Group Equivariant Vision Transformer: Simple and Effectivecited by 3
  6. 2025Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Eventscited by 1
  7. 2025BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensationcited by 0
  8. 2026Compressed-Domain-Aware Online Video Super-Resolutioncited by 0
  9. 2026AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolutioncited by 0