Underwater images often suffer from color cast, low contrast, scattering-induced haze, and texture degradation, which limit the performance of underwater visual perception systems. To address these problems, this study proposes FreqMambaGAN, a frequency-decoupled selective state-space cycle-adversarial network for underwater image enhancement. The proposed method is built upon a CycleGAN-style bidirectional translation framework and introduces a frequency-decoupled Mamba generator to separately model low-frequency color and illumination information and high-frequency texture and edge details. In addition, Efficient Mamba Blocks are embedded into the generator and discriminator to enhance long-range dependency modeling with linear computational complexity. Skip-attention connections are further adopted to preserve shallow spatial details during reconstruction. To improve training stability and imaging plausibility, a multi-stage training strategy is designed by combining supervised warm-up, unpaired cycle-adversarial learning, perceptual regularization, total variation smoothing, and a lightweight physics-inspired consistency constraint based on dark-channel and underwater image-formation priors. Experiments on public underwater image enhancement datasets demonstrate that FreqMambaGAN achieves competitive quantitative performance and visually improved enhancement results in terms of color correction, contrast restoration, haze suppression, and structural preservation. These results indicate that integrating frequency-domain decomposition with selective state-space modeling is effective for underwater image enhancement.
Ye et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: