WaterClear-GS: Optical-Aware Gaussian Splatting for Underwater Reconstruction and Restoration

TL;DR

WaterClear-GS is a novel 3D Gaussian Splatting framework that explicitly models underwater optical effects, enabling high-quality underwater reconstruction and restoration with real-time rendering capabilities.

Contribution

It introduces the first pure 3DGS-based method that incorporates underwater optical properties without auxiliary networks, improving underwater 3D reconstruction and image restoration.

Findings

Achieves state-of-the-art results on benchmark datasets.

Enables real-time underwater 3D reconstruction and restoration.

Effectively models complex underwater optical effects.

Abstract

Underwater 3D reconstruction and appearance restoration are hindered by the complex optical properties of water, such as wavelength-dependent attenuation and scattering. Existing Neural Radiance Fields (NeRF)-based methods struggle with slow rendering speeds and suboptimal color restoration, while 3D Gaussian Splatting (3DGS) inherently lacks the capability to model complex volumetric scattering effects. To address these issues, we introduce WaterClear-GS, the first pure 3DGS-based framework that explicitly integrates underwater optical properties of local attenuation and scattering into Gaussian primitives, eliminating the need for an auxiliary medium network. Our method employs a dual-branch optimization strategy to ensure underwater photometric consistency while naturally recovering water-free appearances. This strategy is enhanced by depth-guided geometry regularization and perception-driven image loss, together with exposure constraints, spatially-adaptive regularization, and physically guided spectral regularization, which collectively enforce local 3D coherence and maintain natural visual perception. Experiments on standard benchmarks and our newly collected dataset demonstrate that WaterClear-GS achieves outstanding performance on both novel view synthesis (NVS) and underwater image restoration (UIR) tasks, while maintaining real-time rendering. The code will be available at https://buaaxrzhang.github.io/WaterClear-GS/.