SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splatting
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.
Code (0)
등록된 구현이 없습니다.
Tasks
3D ReconstructionImage GenerationNovel View SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
NAS-GS: Noise-Aware Sonar Gaussian Splatting
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 ReconstructionZ-Splat: Z-Axis Gaussian Splatting for Camera-Sonar Fusion
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 SynthesisSingle View Seafloor Recovery from Imaging Sonar via Differentiable Rendering
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
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
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