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.

翻译：本文提出SonarSplat，一种用于成像声呐的新型高斯溅射框架，能够实现逼真的新视角合成并模拟声学条纹现象。我们的方法将场景表示为一组具有声学反射率和饱和特性的三维高斯分布。我们开发了一种新颖的方法来高效光栅化高斯分布，生成符合成像声呐声学图像形成模型的距离/方位图像。特别地，我们在高斯溅射框架中提出了一种创新的方位条纹建模方法。我们使用从水下机器人平台在受控测试池和真实河流环境中采集的声呐图像真实数据集对SonarSplat进行评估。与现有技术相比，SonarSplat在图像合成能力上有所提升（PSNR提高3.2 dB），并实现了更精确的三维重建（倒角距离降低77%）。我们还证明了SonarSplat可用于方位条纹消除。