WaterGS: Physically-Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction
文献类型：期刊论文
| 作者 | Wang, S. Q.1; Wu, W. B.1; Shi, M.1; Li, Z. X.2; Wang, Q.1; Zhu, D. M.3,4 |
| 刊名 | COMPUTER GRAPHICS FORUM
 |
| 出版日期 | 2025-10-11 |
| 页码 | 12 |
| 关键词 | CCS Concepts center dot Computing methodologies -> Reconstruction Image-based rendering |
| ISSN号 | 0167-7055 |
| DOI | 10.1111/cgf.70270 |
| 英文摘要 | 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. |
| 资助项目 | Suzhou Science and Technology Program-Frontier Technology Research Project |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001590870000001 |
| 出版者 | WILEY |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/41654]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Shi, M. |
| 作者单位 | 1.North China Elect Power Univ, Beijing, Peoples R China 2.Chinese Acad Agr Sci, Agr Informat Inst, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 4.Taicang ZK Inst Informat & Technol, Taicang, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, S. Q.,Wu, W. B.,Shi, M.,et al. WaterGS: Physically-Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction[J]. COMPUTER GRAPHICS FORUM,2025:12. |
| APA | Wang, S. Q.,Wu, W. B.,Shi, M.,Li, Z. X.,Wang, Q.,&Zhu, D. M..(2025).WaterGS: Physically-Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction.COMPUTER GRAPHICS FORUM,12. |
| MLA | Wang, S. Q.,et al."WaterGS: Physically-Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction".COMPUTER GRAPHICS FORUM (2025):12. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。