paper-with-me

홈 › Papers

SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splatting

2025-03-31 · Advaith V. Sethuraman, Max Rucker, Onur Bagoren, Pou-Chun Kung, Nibarkavi N. B. Amutha, Katherine A. Skinner

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 (52% lower Chamfer Distance). We also demonstrate that SonarSplat can be leveraged for azimuth streak removal.

📄 PDF Abstract BibTeX arXiv:2504.00159

Code (0)

등록된 구현이 없습니다.

Tasks

3D ReconstructionImage GenerationNovel View Synthesis

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

NAS-GS: Noise-Aware Sonar Gaussian Splatting

2026-01-09 · Shida Xu, Jingqi Jiang, Jonatan Scharff Willners, Sen Wang arxiv

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…

Novel View Synthesis3D Reconstruction

Z-Splat: Z-Axis Gaussian Splatting for Camera-Sonar Fusion

2024-04-06 · Ziyuan Qu, Omkar Vengurlekar, Mohamad Qadri, Kevin Zhang 외

Differentiable 3D-Gaussian splatting (GS) is emerging as a prominent technique in computer vision and graphics for reconstructing 3D scenes. GS represents a scene as a set of 3D Gaussians with varying opacities and emplo…

3D geometryAutonomous NavigationNovel View Synthesis

Single View Seafloor Recovery from Imaging Sonar via Differentiable Rendering

2026-05-22 · Sevan Brodjian, Michael Hobley, Pietro Perona arxiv

Sonar is often the only modality suitable for high-resolution imaging underwater due to light attenuation and turbidity. Forward-looking imaging sonar provides measurements over range and horizontal angle but collapses v…

SONIC: Sonar Image Correspondence using Pose Supervised Learning for Imaging Sonars

2023-10-23 · Samiran Gode, Akshay Hinduja, Michael Kaess

In this paper, we address the challenging problem of data association for underwater SLAM through a novel method for sonar image correspondence using learned features. We introduce SONIC (SONar Image Correspondence), a p…

Neural Implicit Surface Reconstruction using Imaging Sonar

2022-09-17 · Mohamad Qadri, Michael Kaess, Ioannis Gkioulekas

We present a technique for dense 3D reconstruction of objects using an imaging sonar, also known as forward-looking sonar (FLS). Compared to previous methods that model the scene geometry as point clouds or volumetric gr…

3D ReconstructionSurface Reconstruction