为视频超分设计首个模型无关的联邦学习框架，兼顾隐私与画质。
FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution
- 基于离散小波变换设计轻量损失函数，保留高频细节。
- 融合多损失的聚合策略，提升全局模型性能（最高+0.89 dB PSNR）。
- 零计算通信开销，适合实际部署于低层视觉任务。
视频超分辨率（VSR）通过利用空间和时间信息增强低分辨率视频。尽管深度学习取得显著进展，但通常需要集中式数据，引发隐私问题。联邦学习（FL）提供隐私保护方案，但通用框架在低层视觉任务中常导致输出模糊。为此，我们提出首个专为VSR设计的模型无关、无状态的联邦学习框架FedVSR。其引入基于离散小波变换（DWT）的轻量损失函数，以在本地训练中更好地保留高频细节；并设计损失感知聚合策略，结合DWT损失与任务特定损失，有效引导全局更新。在多个VSR模型与数据集上的实验表明，FedVSR不仅显著提升感知质量（最高+0.89 dB PSNR，+0.0370 SSIM，-0.0347 LPIPS，4.98 VMAF），且相比同类方法几乎无额外计算与通信开销。结果验证了其在隐私、效率与画质间的平衡潜力，为低层视觉任务中的联邦学习树立新基准。代码已开源：https://github.com/alimd94/FedVSR
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。