TUGS: Physics-based Compact Representation of Underwater Scenes by Tensorized Gaussian

TL;DR

TUGS is a physics-based compact 3D underwater scene representation that enables efficient, high-quality rendering by modeling light interactions and optimizing tensorized data structures.

Contribution

The paper introduces TUGS, a novel underwater scene representation combining physical light modeling with tensorized optimization for improved efficiency and quality.

Findings

TUGS achieves superior reconstruction quality with fewer parameters.

It enables faster rendering speeds and reduced memory usage.

Experiments on real-world datasets validate its effectiveness.

Abstract

Underwater 3D scene reconstruction is crucial for multimedia applications in adverse environments, such as underwater robotic perception and navigation. However, the complexity of interactions between light propagation, water medium, and object surfaces poses significant difficulties for existing methods in accurately simulating their interplay. Additionally, expensive training and rendering costs limit their practical application. Therefore, we propose Tensorized Underwater Gaussian Splatting (TUGS), a compact underwater 3D representation based on physical modeling of complex underwater light fields. TUGS includes a physics-based underwater Adaptive Medium Estimation (AME) module, enabling accurate simulation of both light attenuation and backscatter effects in underwater environments, and introduces Tensorized Densification Strategies (TDS) to efficiently refine the tensorized representation during optimization. TUGS is able to render high-quality underwater images with faster rendering speeds and less memory usage. Extensive experiments on real-world underwater datasets have demonstrated that TUGS can efficiently achieve superior reconstruction quality using a limited number of parameters. The code is available at https://liamlian0727.github.io/TUGS