Revisiting Temporal Alignment for Video Restoration

Kun Zhou, Wenbo Li, Liying Lu, Xiaoguang Han, Jiangbo Lu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 6053-6062

Abstract


Long-range temporal alignment is critical yet challenging for video restoration tasks. Recently, some works attempt to divide the long-range alignment into several sub-alignments and handle them progressively. Although this operation is helpful in modeling distant correspondences, error accumulation is inevitable due to the propagation mechanism. In this work, we present a novel, generic iterative alignment module which employs a gradual refinement scheme for sub-alignments, yielding more accurate motion compensation. To further enhance the alignment accuracy and temporal consistency, we develop a non-parametric re-weighting method, where the importance of each neighboring frame is adaptively evaluated in a spatial-wise way for aggregation. By virtue of the proposed strategies, our model achieves state-of-the-art performance on multiple benchmarks across a range of video restoration tasks including video super-resolution, denoising and deblurring.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2022_CVPR, author = {Zhou, Kun and Li, Wenbo and Lu, Liying and Han, Xiaoguang and Lu, Jiangbo}, title = {Revisiting Temporal Alignment for Video Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {6053-6062} }