Abstract
Accurate depth estimation is fundamental for underwater applications such as robotics and marine exploration. However, underwater imaging suffers from severe degradation due to light attenuation, scattering, and geometric distortion, which is compounded by the scarcity of real stereo data. To address these challenges, we propose Joint Dual-Branch Denoising (JDBD), which is a plug-in framework embedded within dual-branch depth estimation networks. JDBD performs task-aware denoising via bidirectional refinement between a monocular and a stereo pathway: the monocular branch combines Adaptive White Balance and a Red Inverse Channel Prior for color correction and haze suppression, while the stereo branch applies Joint Bilateral Filtering to reduce scattering and preserve edges. Trained on the synthetic UWStereo dataset and evaluated on the real-world SQUID dataset as well as a subset of UWStereo, JDBD achieves high depth estimation accuracy and visual fidelity in underwater scenes, demonstrating robust and adaptable performance across diverse conditions.