Representing underwater 3D scenes is a valuable yet complex task, as attenuation and scattering effects during underwater imaging significantly couple the information of the objects and the water. This coupling presents a significant challenge for existing methods in effectively representing both the objects and the water medium simultaneously.
To address this challenge, we propose Aquatic-GS, a hybrid 3D representation approach for underwater scenes that effectively represents both the objects and the water medium. Specifically, we construct a Neural Water Field (NWF) to implicitly model the water parameters, while extending the latest 3D Gaussian Splatting (3DGS) to model the objects explicitly. Both components are integrated through a physics-based underwater image formation model to represent complex underwater scenes. Moreover, to construct more precise scene geometry and details, we design a Depth-Guided Optimization (DGO) mechanism that uses a pseudo-depth map as auxiliary guidance. After optimization, Aquatic-GS enables the rendering of novel underwater viewpoints and supports restoring the true appearance of underwater scenes, as if the water medium were absent.
Extensive experiments on both simulated and real-world datasets demonstrate that Aquatic-GS surpasses state-of-the-art underwater 3D representation methods, achieving better rendering quality and real-time rendering performance with a 410x increase in speed. Furthermore, regarding underwater image restoration, Aquatic-GS outperforms representative dewatering methods in color correction, detail recovery, and stability.
Below, you can choose different scenes for comparison. On the left, you will see the comparison between 3DGS and Aquatic-GS; on the right, you will see the comparison between SeaThru-NeRF and Aquatic-GS. Please select a scene from the dropdown menu:
Below, you can choose different scenes for comparison. On the left, you can see our Aquatic-GS rendering of the underwater scene (with water) alongside the restored scene (without water). On the right, you can see the comparison between SeaThru-NeRF and Aquatic-GS in underwater scene restoration (de-water). Please select a scene from the dropdown menu:
@article{liu2024aquatic,
author = {Shaohua Liu, Junzhe Lu, Zuoya Gu, Jiajun Li, and Yue Deng},
title = {Aquatic-GS:A Hybrid 3D Representation for Underwater Scenes},
journal = {xxxx},
year = {2024},
}