MoCRA：用于4K全合一视频恢复的组合秩1原子混合模型
MoCRA: Mixture of Compositional Rank-1 Atoms for 4K All-in-One Video Restoration
AI总结：
MoCRA是一种360万参数的4K全合一视频恢复模型，通过频带匹配组合条件与秩1原子字典，无需光流，在UHV-4K-AIO基准上实现了优于基线的PSNR、低扭曲误差与快速4K恢复。
AI中文摘要：
真实世界的视频常存在模糊、下雨、昏暗或噪声问题，而可部署的恢复器需同时满足三个要求：无需退化标签、原生4K输出、播放稳定性。现有方法分别解决这些问题，在联合问题上失效，因为帧间退化读数会翻转，下采样代理会抹去本应去除的雨和噪声，密集时间对齐不适合4K内存，且没有配对基准提出该问题，因此我们构建了UHV-4K-AIO基准：在100个相同的干净4K剪辑上渲染物理建模的雾、雨、传感器噪声和低光，共享深度和运动，其构建揭示了MoCRA的设计基础：雾和低光在激进下采样中保留，而雨和噪声仅存在于原生尺度。我们采用频带匹配的组合条件，将条件容量、计算和监督分配给每种退化所在的频带，一个秩1原子字典，每帧稀疏重组，同时为每剪辑一次的粗分支和浅层原生分辨率细化器提供条件，参数仅360万且无需光流。MoCRA针对所有四个任务训练一次，在11个重新训练的图像和视频基线中取得最佳任务平均PSNR，扭曲误差保持在基于光流的视频模型水平，且从不估计运动，恢复原生4K耗时不到0.5秒，而最快基线耗时1.7秒。
英文摘要：
Real-world video arrives hazy, rainy, dark, or noisy, and a deployable restorer faces three demands at once: no degradation label, native 4K output, and stability in playback. Existing methods answer them separately and break on the joint problem, because per-frame degradation readings flip between frames, downsampled proxies erase the rain and noise they are meant to remove, and dense temporal alignment does not fit 4K memory. No paired benchmark even poses that problem, so we build one. UHV-4K-AIO renders physically modeled haze, rain, sensor noise, and low light over the same 100 clean 4K clips with shared depth and motion, and its construction exposes the split MoCRA is built on: haze and low light survive aggressive downsampling, while rain and noise exist only at native scale. Band-matched compositional conditioning follows, spending conditioning capacity, computation, and supervision in the band where each degradation lives. One dictionary of rank-1 atoms, recomposed sparsely per frame, conditions both a once-per-clip coarse branch and a shallow native-resolution refiner, in 3.6M parameters and with no optical flow. Trained once for all four tasks, MoCRA takes the best task-mean PSNR of eleven retrained image and video baselines, holds warping error at the level of the flow-based video models while never estimating motion, and restores native 4K in under half a second, against 1.7 seconds for the fastest baseline.
