NAS-GS: Noise-Aware Sonar Gaussian Splatting
This addresses the problem of accurate 3D reconstruction in murky water for applications like autonomous navigation and marine archaeology, representing a domain-specific incremental advance.
The paper tackles 3D reconstruction and novel view synthesis from underwater sonar images by proposing NAS-GS, a noise-aware Gaussian splatting framework that introduces a Two-Ways Splatting technique for faster rendering and a Gaussian Mixture Model noise model to handle complex sonar noise patterns. It demonstrates state-of-the-art performance on simulated and real-world offshore sonar scenarios.
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.