Transmission and Color-guided Network for Underwater Image Enhancement

TL;DR

This paper introduces ATDCnet, a novel underwater image enhancement network that combines physics-guided transmission modeling and dynamic color correction to improve image quality in underwater environments.

Contribution

The paper presents a new adaptive transmission-guided network with a dynamic color module and an encoder-decoder structure for simultaneous color restoration and contrast enhancement.

Findings

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

Effectively restores color and contrast in underwater images.

Demonstrates robustness across diverse underwater conditions.

Abstract

In recent years, with the continuous development of the marine industry, underwater image enhancement has attracted plenty of attention. Unfortunately, the propagation of light in water will be absorbed by water bodies and scattered by suspended particles, resulting in color deviation and low contrast. To solve these two problems, we propose an Adaptive Transmission and Dynamic Color guided network (named ATDCnet) for underwater image enhancement. In particular, to exploit the knowledge of physics, we design an Adaptive Transmission-directed Module (ATM) to better guide the network. To deal with the color deviation problem, we design a Dynamic Color-guided Module (DCM) to post-process the enhanced image color. Further, we design an Encoder-Decoder-based Compensation (EDC) structure with attention and a multi-stage feature fusion mechanism to perform color restoration and contrast enhancement simultaneously. Extensive experiments demonstrate the state-of-the-art performance of the ATDCnet on multiple benchmark datasets.