Revisiting Temporal Alignment for Video Restoration
This work addresses error accumulation in video restoration for applications requiring high-quality video processing, representing an incremental improvement over existing methods.
The paper tackles the challenge of long-range temporal alignment in video restoration by introducing an iterative alignment module with gradual refinement and a non-parametric re-weighting method, achieving state-of-the-art performance on benchmarks for tasks like super-resolution, denoising, and deblurring.
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. Our project is available in \url{https://github.com/redrock303/Revisiting-Temporal-Alignment-for-Video-Restoration.git}.