WaterWave: Bridging Underwater Image Enhancement into Video Streams via Wavelet-based Temporal Consistency Field

TL;DR

WaterWave introduces a wavelet-based method to enhance underwater videos by ensuring temporal consistency, improving visual quality and downstream tracking performance without requiring paired training data.

Contribution

The paper proposes a novel implicit wavelet-based temporal consistency field for underwater video enhancement that preserves motion details and corrects flow considering underwater transmission effects.

Findings

Significantly improves underwater video quality.

Enhances downstream tracking accuracy by large margins.

Operates effectively without paired training data.

Abstract

Underwater video pairs are fairly difficult to obtain due to the complex underwater imaging. In this case, most existing video underwater enhancement methods are performed by directly applying the single-image enhancement model frame by frame, but a natural issue is lacking temporal consistency. To relieve the problem, we rethink the temporal manifold inherent in natural videos and observe a temporal consistency prior in dynamic scenes from the local temporal frequency perspective. Building upon the specific prior and no paired-data condition, we propose an implicit representation manner for enhanced video signals, which is conducted in the wavelet-based temporal consistency field, WaterWave. Specifically, under the constraints of the prior, we progressively filter and attenuate the inconsistent components while preserving motion details and scenes, achieving a natural-flowing video. Furthermore, to represent temporal frequency bands more accurately, an underwater flow correction module is designed to rectify estimated flows considering the transmission in underwater scenes. Extensive experiments demonstrate that WaterWave significantly enhances the quality of videos generated using single-image underwater enhancements. Additionally, our method demonstrates high potential in downstream underwater tracking tasks, such as UOSTrack and MAT, outperforming the original video by a large margin, i.e., 19.7% and 9.7% on precise respectively.