mlsanityData to 14 Oct 2026

Efficient Video Super-Resolution through Recurrent Latent Space Propagation

arXiv 1909.08080 ↗First posted 17 Sep 2019eess.IVcited by 69

Not on the map. Why?

Abstract (arXiv)

With the recent trend for ultra high definition displays, the demand for high quality and efficient video super-resolution (VSR) has become more important than ever. Previous methods adopt complex motion compensation strategies to exploit temporal information when estimating the missing high frequency details. However, as the motion estimation problem is a highly challenging problem, inaccurate motion compensation may affect the performance of VSR algorithms. Furthermore, the complex motion compensation module may also introduce a heavy computational burden, which limits the application of these methods in real systems. In this paper, we propose an efficient recurrent latent space propagation (RLSP) algorithm for fast VSR. RLSP introduces high-dimensional latent states to propagate temporal information between frames in an implicit manner. Our experimental results show that RLSP is a highly efficient and effective method to deal with the VSR problem. We outperform current state-of-the-art method DUF with over 70x speed-up.

Key facts. Cited by 69 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 14; 2023: 15; 2024: 10; 2025: 19; 2026: 2.

69 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. 2023A Comprehensive Survey on Segment Anything Model for Vision and Beyondcited by 64
  5. 2022Learning Trajectory-Aware Transformer for Video Super-Resolutioncited by 61
  6. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
  7. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 43
  8. 2023Enhancing Video Super-Resolution via Implicit Resampling-based Alignmentcited by 35
  9. 2024RealViformer: Investigating Attention for Real-World Video Super-Resolutioncited by 33
  10. 2021Omniscient Video Super-Resolutioncited by 30
  11. 2024Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attentioncited by 29
  12. 2024FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurringcited by 28
38 more
  1. 2021COMISR: Compression-Informed Video Super-Resolutioncited by 26
  2. 2022Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-ahead Forward Onescited by 24
  3. 2022AnimeSR: Learning Real-World Super-Resolution Models for Animation Videoscited by 23
  4. 2023Can SAM Boost Video Super-Resolution?cited by 21
  5. 2022Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modelingcited by 20
  6. 2021Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 19
  7. 2021Self-Conditioned Probabilistic Learning of Video Rescalingcited by 19
  8. 2023Precipitation Downscaling with Spatiotemporal Video Diffusioncited by 19
  9. 2022Temporal Consistency Learning of inter-frames for Video Super-Resolutioncited by 16
  10. 2025One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolutioncited by 15
  11. 2022Structured Sparsity Learning for Efficient Video Super-Resolutioncited by 14
  12. 2025UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Spacecited by 14
  13. 2024Learning Truncated Causal History Model for Video Restorationcited by 13
  14. 2022Online Video Super-Resolution with Convolutional Kernel Bypass Graftcited by 12
  15. 2023Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolutioncited by 8
  16. 2023TMP: Temporal Motion Propagation for Online Video Super-Resolutioncited by 8
  17. 2025Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusioncited by 7
  18. 2021Stable Long-Term Recurrent Video Super-Resolutioncited by 6
  19. 2022A Codec Information Assisted Framework for Efficient Compressed Video Super-Resolutioncited by 6
  20. 2023Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representationscited by 5
  21. 2023RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolutioncited by 5
  22. 2025A Survey of Deep Learning Video Super-Resolutioncited by 5
  23. 2025Blind Video Super-Resolution based on Implicit Kernelscited by 4
  24. 2021Deep Unrolled Network for Video Super-Resolutioncited by 3
  25. 2022Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Reportcited by 3
  26. 2023Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolutioncited by 3
  27. 2024Bilateral Event Mining and Complementary for Event Stream Super-Resolutioncited by 3
  28. 2025Rethinking Video Super-Resolution: Towards Diffusion-Based Methods without Motion Alignmentcited by 3
  29. 2025Ultralight Polarity-Split Neuromorphic SNN for Event-Stream Super-Resolutioncited by 3
  30. 2025OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolutioncited by 3
  31. 2021PP-MSVSR: Multi-Stage Video Super-Resolutioncited by 2
  32. 2023Efficient neural supersampling on a novel gaming datasetcited by 2
  33. 2023Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reductioncited by 2
  34. 2024Spatio-Temporal Distortion Aware Omnidirectional Video Super-Resolutioncited by 2
  35. 2025Spatial Degradation-Aware and Temporal Consistent Diffusion Model for Compressed Video Super-Resolutioncited by 2
  36. 2025Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Featurescited by 2
  37. 2025CreativeVR: Diffusion-Prior-Guided Approach for Structure and Motion Restoration in Generative and Real Videoscited by 2
  38. 2023ReBotNet: Fast Real-time Video Enhancementcited by 1

50 most cited of 69 All 69 (JSON)