WaterGS: Physically-Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction

Loading...
Thumbnail Image
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Reconstructing underwater object geometry from multi-view images is a long-standing challenge in computer graphics, primarily due to image degradation caused by underwater scattering, blur, and color shift. These degradations severely impair feature extraction and multi-view consistency. Existing methods typically rely on pre-trained image enhancement models as a preprocessing step, but often struggle with robustness under varying water conditions. To overcome these limitations, we propose WaterGS, a novel framework for underwater surface reconstruction that jointly recovers accurate 3D geometry and restores true object colors. The core of our approach lies in introducing a Physically-Based imaging model into the rendering process of 2D Gaussian Splatting. This enables accurate separation of true object colors from water-induced distortions, thereby facilitating more robust photometric alignment and denser geometric reconstruction across views. Building upon this improved photometric consistency, we further introduce a Gaussian bundle adjustment scheme guided by our physical model to jointly optimize camera poses and geometry, enhancing reconstruction accuracy. Extensive experiments on synthetic and real-world datasets show that WaterGS achieves robust, high-fidelity reconstruction directly from raw underwater images, outperforming prior approaches in both geometric accuracy and visual consistency.
Description

CCS Concepts: Computing methodologies → Reconstruction; Image-based rendering

        
@article{
10.1111:cgf.70270
, journal = {Computer Graphics Forum}, title = {{
WaterGS: Physically-Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction
}}, author = {
, Su Qing Wang
and
Wu, Wen Bin
and
Shi, Min
and
Li, Zhao Xin
and
Wang, Qi
and
Zhu, Deng Ming
}, year = {
2025
}, publisher = {
The Eurographics Association and John Wiley & Sons Ltd.
}, ISSN = {
1467-8659
}, DOI = {
10.1111/cgf.70270
} }
Citation
Collections