WaterFlow: Explicit Physics-Prior Rectified Flow for Underwater Saliency Mask Generation
This addresses domain-specific challenges in underwater computer vision for applications like marine robotics.
The paper tackles underwater salient object detection by incorporating explicit physics priors and temporal modeling into a rectified flow framework, achieving a 0.072 gain in S_m on the USOD10K dataset.
Underwater Salient Object Detection (USOD) faces significant challenges, including underwater image quality degradation and domain gaps. Existing methods tend to ignore the physical principles of underwater imaging or simply treat degradation phenomena in underwater images as interference factors that must be eliminated, failing to fully exploit the valuable information they contain. We propose WaterFlow, a rectified flow-based framework for underwater salient object detection that innovatively incorporates underwater physical imaging information as explicit priors directly into the network training process and introduces temporal dimension modeling, significantly enhancing the model's capability for salient object identification. On the USOD10K dataset, WaterFlow achieves a 0.072 gain in S_m, demonstrating the effectiveness and superiority of our method. The code will be published after the acceptance.