MuLA-GAN: Multi-Level Attention GAN for Enhanced Underwater Visibility

TL;DR

MuLA-GAN is a novel multi-level attention GAN that significantly improves underwater image quality by focusing on relevant features, outperforming existing methods in various datasets and applications.

Contribution

Introduces MuLA-GAN, integrating Multi-Level Attention into GANs for superior underwater image enhancement, addressing a key research gap with extensive evaluations.

Findings

Achieves higher PSNR and SSIM scores than state-of-the-art methods.

Excels in diverse datasets including UIEB and U45.

Demonstrates robustness in bio-fouling and aquaculture environments.

Abstract

The underwater environment presents unique challenges, including color distortions, reduced contrast, and blurriness, hindering accurate analysis. In this work, we introduce MuLA-GAN, a novel approach that leverages the synergistic power of Generative Adversarial Networks (GANs) and Multi-Level Attention mechanisms for comprehensive underwater image enhancement. The integration of Multi-Level Attention within the GAN architecture significantly enhances the model's capacity to learn discriminative features crucial for precise image restoration. By selectively focusing on relevant spatial and multi-level features, our model excels in capturing and preserving intricate details in underwater imagery, essential for various applications. Extensive qualitative and quantitative analyses on diverse datasets, including UIEB test dataset, UIEB challenge dataset, U45, and UCCS dataset, highlight the superior performance of MuLA-GAN compared to existing state-of-the-art methods. Experimental evaluations on a specialized dataset tailored for bio-fouling and aquaculture applications demonstrate the model's robustness in challenging environmental conditions. On the UIEB test dataset, MuLA-GAN achieves exceptional PSNR (25.59) and SSIM (0.893) scores, surpassing Water-Net, the second-best model, with scores of 24.36 and 0.885, respectively. This work not only addresses a significant research gap in underwater image enhancement but also underscores the pivotal role of Multi-Level Attention in enhancing GANs, providing a novel and comprehensive framework for restoring underwater image quality.