Revisiting Temporal Alignment for Video Restoration

TL;DR

This paper introduces a novel iterative alignment module with a gradual refinement scheme and adaptive re-weighting for improved temporal alignment in video restoration, achieving state-of-the-art results.

Contribution

It proposes a generic iterative alignment method with a refinement scheme and adaptive re-weighting to enhance accuracy and consistency in video restoration tasks.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Effective in video super-resolution, denoising, and deblurring.

Improves temporal alignment accuracy and reduces error accumulation.

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. Our project is available in \url{https://github.com/redrock303/Revisiting-Temporal-Alignment-for-Video-Restoration.git}.