Underwater image enhancement using Divide-and-Conquer network

Abstract

Underwater image enhancement has become the requirement for more people to have a better visual experience or to extract information. However, underwater images often suffer from the mixture of color distortion and blurred quality degradation due to the external environment (light attenuation, background noise and the type of water). To solve the above problem, we design a Divide-and-Conquer network (DC-net) for enhancing underwater image, which mainly consists of a texture network, a color network and a refinement network. Specifically, the multi-axis attention block is presented in the texture network, which combine different region/channel features into a single stream structure. And the color network employs an adaptive 3D look-up table method to obtain the color enhanced results. Meanwhile, the refinement network is presented to focus on image features of ground truth. Compared to state-of-the-art (SOTA) underwater image enhance methods, our proposed method can obtain the better visual quality of underwater images and better qualitative and quantitative performance. The code is publicly available at https://github.com/zhengshijian1993/DC-Net.

Underwater Fish Object Detection with Degraded Prior Knowledge

“…Take underwater scenes as an example (depicted in Figure 1): they exhibit various degradation issues and diverse styles. By employing two restoration techniques, Learnable Full-frequency Transformer Dual Generative Adversarial Network (LFT-DGAN) [9], and Divide-and-Conquer network (DC-net) [10], higher-quality images can be generated. Each column represents the same scene but with varying detection outcomes using the cascaded RCNN detector, suggesting a potential link between underwater image restoration and object detection.…”