NAS-GS: Noise-Aware Sonar Gaussian Splatting

TL;DR

NAS-GS introduces a noise-aware Gaussian splatting framework tailored for underwater sonar imaging, effectively modeling complex noise and improving 3D reconstruction and view synthesis speed and quality.

Contribution

The paper presents a novel Two-Ways Splatting technique and a GMM-based noise model specifically designed for sonar imaging challenges, advancing the state-of-the-art in underwater 3D reconstruction.

Findings

Achieves superior novel view synthesis results on real-world sonar data.

Improves reconstruction accuracy by modeling complex sonar noise patterns.

Speeds up rendering without compromising quality.

Abstract

Underwater sonar imaging plays a crucial role in various applications, including autonomous navigation in murky water, marine archaeology, and environmental monitoring. However, the unique characteristics of sonar images, such as complex noise patterns and the lack of elevation information, pose significant challenges for 3D reconstruction and novel view synthesis. In this paper, we present NAS-GS, a novel Noise-Aware Sonar Gaussian Splatting framework specifically designed to address these challenges. Our approach introduces a Two-Ways Splatting technique that accurately models the dual directions for intensity accumulation and transmittance calculation inherent in sonar imaging, significantly improving rendering speed without sacrificing quality. Moreover, we propose a Gaussian Mixture Model (GMM) based noise model that captures complex sonar noise patterns, including side-lobes, speckle, and multi-path noise. This model enhances the realism of synthesized images while preventing 3D Gaussian overfitting to noise, thereby improving reconstruction accuracy. We demonstrate state-of-the-art performance on both simulated and real-world large-scale offshore sonar scenarios, achieving superior results in novel view synthesis and 3D reconstruction.