DualPhys-GS: Dual Physically-Guided 3D Gaussian Splatting for Underwater Scene Reconstruction
Preprint
Abstract
In 3D reconstruction of underwater scenes, traditional methods based on atmospheric optical models cannot effectively deal with the selective attenuation of light wavelengths and the effect of suspended particle scattering, which are unique to the water medium, and lead to color distortion, geometric artifacts, and collapsing phenomena at long distances. We propose the DualPhys-GS framework to achieve high-quality underwater reconstruction through a dual-path optimization mechanism. Our approach further develops a dual feature-guided attenuation-scattering modeling mechanism, the RGB-guided attenuation optimization model combines RGB features and depth information and can handle edge and structural details. In contrast, the multi-scale depth-aware scattering model captures scattering effects at different scales using a feature pyramid network and an attention mechanism. Meanwhile, we design several special loss functions. The attenuation scattering consistency loss ensures physical consistency. The water body type adaptive loss dynamically adjusts the weighting coefficients. The edge-aware scattering loss is used to maintain the sharpness of structural edges. The multi-scale feature loss helps to capture global and local structural information. In addition, we design a scene adaptive mechanism that can automatically identify the water-body-type characteristics (e.g., clear coral reef waters or turbid coastal waters) and dynamically adjust the scattering and attenuation parameters and optimization strategies. Experimental results show that our method outperforms existing methods in several metrics, especially in suspended matter-dense regions and long-distance scenes, and the reconstruction quality is significantly improved.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular VideoProceedings of the AAAI Conference on Artificial Intelligence, 2026
- ReCap: Better Gaussian Relighting with Cross-Environment Captures2025
- SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model2025
- WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting2025
- WaterNeRF: Neural Radiance Fields for Underwater Scenes2023
- Beyond NeRF Underwater: Learning Neural Reflectance Fields for True Color Correction of Marine ImageryIEEE Robotics and Automation Letters, 2023
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingACM Transactions on Graphics, 2023
- WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater ImagesIEEE Robotics and Automation Letters, 2017
- Multi-View Stereo: A TutorialFoundations and Trends in Computer Graphics and Vision, 2015
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004