End-To-End Underwater Video Enhancement: Dataset and Model

TL;DR

This paper introduces a new dataset and a novel model for underwater video enhancement, leveraging inter-frame relationships to improve video quality, and demonstrates its effectiveness through extensive experiments.

Contribution

We created the first synthetic underwater video dataset with ground-truth references and developed UVENet, a model that enhances videos by exploiting inter-frame information.

Findings

UVENet outperforms existing methods on synthetic and real videos.

The SUVE dataset provides a valuable resource for UVE research.

Inter-frame modeling significantly improves enhancement quality.

Abstract

Underwater video enhancement (UVE) aims to improve the visibility and frame quality of underwater videos, which has significant implications for marine research and exploration. However, existing methods primarily focus on developing image enhancement algorithms to enhance each frame independently. There is a lack of supervised datasets and models specifically tailored for UVE tasks. To fill this gap, we construct the Synthetic Underwater Video Enhancement (SUVE) dataset, comprising 840 diverse underwater-style videos paired with ground-truth reference videos. Based on this dataset, we train a novel underwater video enhancement model, UVENet, which utilizes inter-frame relationships to achieve better enhancement performance. Through extensive experiments on both synthetic and real underwater videos, we demonstrate the effectiveness of our approach. This study represents the first comprehensive exploration of UVE to our knowledge. The code is available at https://anonymous.4open.science/r/UVENet.