SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splatting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sethuraman, Advaith V., Rucker, Max, Bagoren, Onur, Kung, Pou-Chun, Amutha, Nibarkavi N. B., Skinner, Katherine A.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909883721318400
author Sethuraman, Advaith V.
Rucker, Max
Bagoren, Onur
Kung, Pou-Chun
Amutha, Nibarkavi N. B.
Skinner, Katherine A.
author_facet Sethuraman, Advaith V.
Rucker, Max
Bagoren, Onur
Kung, Pou-Chun
Amutha, Nibarkavi N. B.
Skinner, Katherine A.
contents In this paper, we present SonarSplat, a novel Gaussian splatting framework for imaging sonar that demonstrates realistic novel view synthesis and models acoustic streaking phenomena. Our method represents the scene as a set of 3D Gaussians with acoustic reflectance and saturation properties. We develop a novel method to efficiently rasterize Gaussians to produce a range/azimuth image that is faithful to the acoustic image formation model of imaging sonar. In particular, we develop a novel approach to model azimuth streaking in a Gaussian splatting framework. We evaluate SonarSplat using real-world datasets of sonar images collected from an underwater robotic platform in a controlled test tank and in a real-world river environment. Compared to the state-of-the-art, SonarSplat offers improved image synthesis capabilities (+3.2 dB PSNR) and more accurate 3D reconstruction (77% lower Chamfer Distance). We also demonstrate that SonarSplat can be leveraged for azimuth streak removal.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00159
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splatting
Sethuraman, Advaith V.
Rucker, Max
Bagoren, Onur
Kung, Pou-Chun
Amutha, Nibarkavi N. B.
Skinner, Katherine A.
Computer Vision and Pattern Recognition
In this paper, we present SonarSplat, a novel Gaussian splatting framework for imaging sonar that demonstrates realistic novel view synthesis and models acoustic streaking phenomena. Our method represents the scene as a set of 3D Gaussians with acoustic reflectance and saturation properties. We develop a novel method to efficiently rasterize Gaussians to produce a range/azimuth image that is faithful to the acoustic image formation model of imaging sonar. In particular, we develop a novel approach to model azimuth streaking in a Gaussian splatting framework. We evaluate SonarSplat using real-world datasets of sonar images collected from an underwater robotic platform in a controlled test tank and in a real-world river environment. Compared to the state-of-the-art, SonarSplat offers improved image synthesis capabilities (+3.2 dB PSNR) and more accurate 3D reconstruction (77% lower Chamfer Distance). We also demonstrate that SonarSplat can be leveraged for azimuth streak removal.
title SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.00159