Feature Attention Network (FA-Net): A Deep-Learning Based Approach for Underwater Single Image Enhancement

TL;DR

This paper introduces FA-Net, a deep learning model with feature attention mechanisms, designed to enhance underwater images by focusing on high-frequency details and addressing complex underwater conditions.

Contribution

The paper proposes a novel Residual Feature Attention Block (RFAB) with channel and pixel attention for improved underwater image enhancement.

Findings

FA-Net outperforms previous methods in accuracy.

The RFAB effectively emphasizes high-frequency information.

Experimental results demonstrate superior qualitative and quantitative performance.

Abstract

Underwater image processing and analysis have been a hotspot of study in recent years, as more emphasis has been focused to underwater monitoring and usage of marine resources. Compared with the open environment, underwater image encountered with more complicated conditions such as light abortion, scattering, turbulence, nonuniform illumination and color diffusion. Although considerable advances and enhancement techniques achieved in resolving these issues, they treat low-frequency information equally across the entire channel, which results in limiting the network's representativeness. We propose a deep learning and feature-attention-based end-to-end network (FA-Net) to solve this problem. In particular, we propose a Residual Feature Attention Block (RFAB), containing the channel attention, pixel attention, and residual learning mechanism with long and short skip connections. RFAB allows the network to focus on learning high-frequency information while skipping low-frequency information on multi-hop connections. The channel and pixel attention mechanism considers each channel's different features and the uneven distribution of haze over different pixels in the image. The experimental results shows that the FA-Net propose by us provides higher accuracy, quantitatively and qualitatively and superiority to previous state-of-the-art methods.