WaterGS: Physically-Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction
| dc.contributor.author | , Su Qing Wang | en_US |
| dc.contributor.author | Wu, Wen Bin | en_US |
| dc.contributor.author | Shi, Min | en_US |
| dc.contributor.author | Li, Zhao Xin | en_US |
| dc.contributor.author | Wang, Qi | en_US |
| dc.contributor.author | Zhu, Deng Ming | en_US |
| dc.contributor.editor | Christie, Marc | en_US |
| dc.contributor.editor | Pietroni, Nico | en_US |
| dc.contributor.editor | Wang, Yu-Shuen | en_US |
| dc.date.accessioned | 2025-10-07T05:03:31Z | |
| dc.date.available | 2025-10-07T05:03:31Z | |
| dc.date.issued | 2025 | |
| dc.description.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. | en_US |
| dc.description.number | 7 | |
| dc.description.sectionheaders | Gaussian Splatting | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 44 | |
| dc.identifier.doi | 10.1111/cgf.70270 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 12 pages | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.70270 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.1111/cgf70270 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | CCS Concepts: Computing methodologies → Reconstruction; Image-based rendering | |
| dc.subject | Computing methodologies → Reconstruction | |
| dc.subject | Image | |
| dc.subject | based rendering | |
| dc.title | WaterGS: Physically-Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction | en_US |