End-To-End Underwater Video Enhancement: Dataset and Model
This work addresses the lack of supervised datasets and models for underwater video enhancement, which is important for marine research and exploration, and is incremental as it builds on existing image enhancement methods.
The paper tackles the problem of underwater video enhancement by constructing the SUVE dataset with 840 synthetic videos and proposing UVENet, a model that leverages inter-frame relationships, demonstrating effectiveness in experiments on synthetic and real videos.
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.