mlsanityData to 14 Oct 2026

FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution

arXiv 2503.13745 ↗First posted 17 Mar 2025cs.CV cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Video super-resolution (VSR) aims to enhance low-resolution videos by leveraging both spatial and temporal information. While deep learning has led to impressive progress, it typically requires centralized data, which raises privacy concerns. Federated learning (FL) offers a privacy-friendly solution, but general FL frameworks often struggle with low-level vision tasks, resulting in blurry, low-quality outputs. To address this, we introduce FedVSR, the first FL framework specifically designed for VSR. It is model-agnostic and stateless, and introduces a lightweight loss function based on the Discrete Wavelet Transform (DWT) to better preserve high-frequency details during local training. Additionally, a loss-aware aggregation strategy combines both DWT-based and task-specific losses to guide global updates effectively. Extensive experiments across multiple VSR models and datasets show that FedVSR not only improves perceptual video quality (up to +0.89 dB PSNR, +0.0370 SSIM, -0.0347 LPIPS and 4.98 VMAF) but also achieves these gains with close to zero computation and communication overhead compared to its rivals. These results demonstrate FedVSR's potential to bridge the gap between privacy, efficiency, and perceptual quality, setting a new benchmark for federated learning in low-level vision tasks. The code is available at: https://github.com/alimd94/FedVSR

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 43 of its 75 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

43 of 75 references.

References · 43

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2017Deep Image Priorcited by 1,098
  5. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  6. 2021Model-Contrastive Federated Learningcited by 766
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  8. 2021Merging Models with Fisher-Weighted Averagingcited by 621
  9. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  10. 2019Fair Resource Allocation in Federated Learningcited by 394
  11. 2017Stable Architectures for Deep Neural Networkscited by 341
  12. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
31 more
  1. 2022VRT: A Video Restoration Transformercited by 220
  2. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 170
  3. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 134
  4. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 132
  5. 2022Improving Generalization in Federated Learning by Seeking Flat Minimacited by 98
  6. 2023Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restorationcited by 88
  7. 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 67
  8. 2019Active Federated Learningcited by 63
  9. 2022Learning Trajectory-Aware Transformer for Video Super-Resolutioncited by 61
  10. 2023Revisiting Weighted Aggregation in Federated Learning with Neural Networkscited by 58
  11. 2020Video Super Resolution Based on Deep Learning: A Comprehensive Surveycited by 54
  12. 2023Learning Federated Visual Prompt in Null Space for MRI Reconstructioncited by 40
  13. 2020SAINT: Spatially Aware Interpolation NeTwork for Medical Slice Synthesiscited by 37
  14. 2021Specificity-Preserving Federated Learning for MR Image Reconstructioncited by 35
  15. 2023Enhancing Video Super-Resolution via Implicit Resampling-based Alignmentcited by 35
  16. 2022Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescited by 30
  17. 2021A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian Regularizationcited by 27
  18. 2020Choosing the Sample with Lowest Loss makes SGD Robustcited by 26
  19. 2021Federated Learning for Face Recognition with Gradient Correctioncited by 24
  20. 2018Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Networkcited by 16
  21. 2023A Survey for Federated Learning Evaluations: Goals and Measurescited by 16
  22. 2024An Improved Empirical Fisher Approximation for Natural Gradient Descentcited by 15
  23. 2021A Non-parametric View of FedAvg and FedProx: Beyond Stationary Pointscited by 13
  24. 2024The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscapecited by 13
  25. 2024Not All Federated Learning Algorithms Are Created Equal: A Performance Evaluation Studycited by 10
  26. 2023A Survey on Model-heterogeneous Federated Learning: Problems, Methods, and Prospectscited by 9
  27. 2023Edge-Based Video Analytics: A Surveycited by 8
  28. 2023Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learningcited by 7
  29. 2022Dual Perceptual Loss for Single Image Super-Resolution Using ESRGANcited by 3
  30. 2024Federated Learning for Blind Image Super-Resolutioncited by 2
  31. 2024Reversing the Damage: A QP-Aware Transformer-Diffusion Approach for 8K Video Restoration under Codec Compressioncited by 2

Built on by

Not cited yet.