RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Zhuodong, Wang, Haoran, Huang, Guoxi, Seymour, Brett, Anantrasirichai, Nantheera
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916926933958656
author Jiang, Zhuodong
Wang, Haoran
Huang, Guoxi
Seymour, Brett
Anantrasirichai, Nantheera
author_facet Jiang, Zhuodong
Wang, Haoran
Huang, Guoxi
Seymour, Brett
Anantrasirichai, Nantheera
contents Reconstructing high-fidelity underwater scenes remains a challenging task due to light absorption, scattering, and limited visibility inherent in aquatic environments. This paper presents an enhanced Gaussian Splatting-based framework that improves both the visual quality and geometric accuracy of deep underwater rendering. We propose decoupled learning for RGB channels, guided by the physics of underwater attenuation, to enable more accurate colour restoration. To address sparse-view limitations and improve view consistency, we introduce a frame interpolation strategy with a novel adaptive weighting scheme. Additionally, we introduce a new loss function aimed at reducing noise while preserving edges, which is essential for deep-sea content. We also release a newly collected dataset, Submerged3D, captured specifically in deep-sea environments. Experimental results demonstrate that our framework consistently outperforms state-of-the-art methods with PSNR gains up to 1.90dB, delivering superior perceptual quality and robustness, and offering promising directions for marine robotics and underwater visual analytics. The code of RUSplatting is available at https://github.com/theflash987/RUSplatting and the dataset Submerged3D can be downloaded at https://zenodo.org/records/15482420.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15737
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene Reconstruction
Jiang, Zhuodong
Wang, Haoran
Huang, Guoxi
Seymour, Brett
Anantrasirichai, Nantheera
Computer Vision and Pattern Recognition
Reconstructing high-fidelity underwater scenes remains a challenging task due to light absorption, scattering, and limited visibility inherent in aquatic environments. This paper presents an enhanced Gaussian Splatting-based framework that improves both the visual quality and geometric accuracy of deep underwater rendering. We propose decoupled learning for RGB channels, guided by the physics of underwater attenuation, to enable more accurate colour restoration. To address sparse-view limitations and improve view consistency, we introduce a frame interpolation strategy with a novel adaptive weighting scheme. Additionally, we introduce a new loss function aimed at reducing noise while preserving edges, which is essential for deep-sea content. We also release a newly collected dataset, Submerged3D, captured specifically in deep-sea environments. Experimental results demonstrate that our framework consistently outperforms state-of-the-art methods with PSNR gains up to 1.90dB, delivering superior perceptual quality and robustness, and offering promising directions for marine robotics and underwater visual analytics. The code of RUSplatting is available at https://github.com/theflash987/RUSplatting and the dataset Submerged3D can be downloaded at https://zenodo.org/records/15482420.
title RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.15737