提出分阶段去噪框架，解决视频去噪中时空矛盾问题
Frames2Residual: Spatiotemporal Decoupling for Self-Supervised Video Denoising
- 分两阶段训练：先建模帧间一致性，再恢复帧内细节
- 在sRGB和raw数据集上超越现有自监督方法
- 适合需要保留纹理细节的视频去噪场景
自监督视频去噪方法通常将图像级框架扩展到时序维度，但难以兼顾帧间一致性与帧内空间特异性。现有视频盲区网络（BSNs）需遮蔽中心像素以保证噪声独立性，这限制了空间信息用于纹理恢复，破坏了时空关联并导致纹理丢失。为此，我们提出帧到残差（F2R）框架，通过显式分离自监督训练为两个阶段：盲时序一致性建模与非盲空间纹理恢复。第一阶段采用帧级盲策略，学习帧间一致性并生成时序一致的锚点；第二阶段利用该锚点安全地重新引入中心帧，恢复帧内高频空间残差，同时保持时序稳定性。大量实验表明，该解耦策略使F2R在sRGB与raw视频基准上均优于现有自监督方法。
原文摘要 · Abstract (English)
Self-supervised video denoising methods typically extend image-based frameworks into the temporal dimension, yet they often struggle to integrate inter-frame temporal consistency with intra-frame spatial specificity. Existing Video Blind-Spot Networks (BSNs) require noise independence by masking the center pixel, this constraint prevents the use of spatial evidence for texture recovery, thereby severing spatiotemporal correlations and causing texture loss. To address this, we propose Frames2Residual (F2R), a spatiotemporal decoupling framework that explicitly divides self-supervised training into two distinct stages: blind temporal consistency modeling and non-blind spatial texture recovery. In Stage 1, a blind temporal estimator learns inter-frame consistency using a frame-wise blind strategy, producing a temporally consistent anchor. In Stage 2, a non-blind spatial refiner leverages this anchor to safely reintroduce the center frame and recover intra-frame high-frequency spatial residuals while preserving temporal stability. Extensive experiments demonstrate that our decoupling strategy allows F2R to outperform existing self-supervised methods on both sRGB and raw video benchmarks.
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。