O-Mamba: O-shape State-Space Model for Underwater Image Enhancement

TL;DR

O-Mamba introduces an O-shaped dual-branch network leveraging state-space models to separately model spatial and cross-channel information, significantly improving underwater image enhancement performance.

Contribution

It proposes a novel O-shaped dual-branch framework with multi-scale mutual promotion modules for better modeling of spatial and cross-channel dependencies in underwater images.

Findings

Achieves state-of-the-art results on underwater image enhancement benchmarks.

Effectively models cross-channel dependencies using state-space models.

Enhances multi-scale information utilization through cyclic optimization.

Abstract

Underwater image enhancement (UIE) face significant challenges due to complex underwater lighting conditions. Recently, mamba-based methods have achieved promising results in image enhancement tasks. However, these methods commonly rely on Vmamba, which focuses only on spatial information modeling and struggles to deal with the cross-color channel dependency problem in underwater images caused by the differential attenuation of light wavelengths, limiting the effective use of deep networks. In this paper, we propose a novel UIE framework called O-mamba. O-mamba employs an O-shaped dual-branch network to separately model spatial and cross-channel information, utilizing the efficient global receptive field of state-space models optimized for underwater images. To enhance information interaction between the two branches and effectively utilize multi-scale information, we design a Multi-scale Bi-mutual Promotion Module. This branch includes MS-MoE for fusing multi-scale information within branches, Mutual Promotion module for interaction between spatial and channel information across branches, and Cyclic Multi-scale optimization strategy to maximize the use of multi-scale information. Extensive experiments demonstrate that our method achieves state-of-the-art (SOTA) results.The code is available at https://github.com/chenydong/O-Mamba.