DualPhys-GS: Dual Physically-Guided 3D Gaussian Splatting for Underwater Scene Reconstruction
Underwater 3D reconstruction suffers from severe color distortion, geometric artifacts, and structural collapse due to wavelength-selective absorption and scattering by suspended particles. Method: This paper proposes a dual physics-guided 3D Gaussian splatting framework. It introduces two parallel optimization pathways: RGB-guided wavelength attenuation modeling and multi-scale depth-aware scattering modeling, integrated with adaptive water-type classification and dynamic parameter adjustment. The architecture incorporates a feature pyramid network, attention mechanisms, and three novel losses—edge-aware scattering loss, multi-scale feature loss, and physics-consistency constraint loss. Results: Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches in turbid waters and at long distances, achieving substantial improvements in reconstruction accuracy and visual fidelity. It effectively mitigates chromatic distortion and geometric collapse, and—uniquely—achieves synergistic enhancement of physical interpretability and neural rendering performance.