UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction

Haoran Wang, Nantheera Anantrasirichai, Fan Zhang, David Bull; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 3280-3289

Abstract


3D Gaussian splatting (3DGS) offers the capability to achieve real-time high quality 3D scene rendering. However 3DGS assumes that the scene is in a clear medium environment and struggles to generate satisfactory representations in underwater scenes where light absorption and scattering are prevalent and moving objects are involved. To overcome these we introduce a novel Gaussian Splatting-based method UW-GS designed specifically for underwater applications. It introduces a color appearance that models distance-dependent color variation employs a new physics-based density control strategy to enhance clarity for distant objects and uses a binary motion mask to handle dynamic content. Optimized with a well-designed loss function supporting for scattering media and strengthened by pseudo-depth maps UW-GS outperforms existing methods with PSNR gains up to 1.26dB. To fully verify the effectiveness of the model we also developed a new underwater dataset S-UW with dynamic object masks. The code of UW-GS and S-UW will be available at https://github.com/WangHaoran16/UW-GS.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Haoran and Anantrasirichai, Nantheera and Zhang, Fan and Bull, David}, title = {UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3280-3289} }