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

doi:10.1111/cgf.70270

	WaterGS: Physically-Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction
	Wang, S. Q.1; Wu, W. B.1; Shi, M.1; Li, Z. X.2; Wang, Q.1; Zhu, D. M.3,4
	2025-10-11
发表期刊	COMPUTER GRAPHICS FORUM
ISSN	0167-7055
页码	12
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.
关键词	CCS Concepts center dot Computing methodologies -> Reconstruction Image-based rendering
DOI	10.1111/cgf.70270
收录类别	SCI
语种	英语
资助项目	Suzhou Science and Technology Program-Frontier Technology Research Project
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:001590870000001
出版者	WILEY
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41655
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.