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

TL;DR

This paper introduces RUSplatting, a robust 3D Gaussian Splatting framework for underwater scene reconstruction that enhances visual quality, geometric accuracy, and view consistency in sparse-view deep-sea environments.

Contribution

It proposes decoupled RGB learning guided by underwater physics, a novel frame interpolation with adaptive weighting, and a new noise-reducing loss function, along with a new deep-sea dataset.

Findings

Outperforms state-of-the-art methods with up to 1.90dB PSNR improvement

Achieves superior perceptual quality and robustness in underwater scenes

Provides a new dataset for deep-sea scene reconstruction

Abstract

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.