paper-with-me

홈 › Papers

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, 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.

📄 PDF Abstract BibTeX arXiv:2601.06285

Code (0)

등록된 구현이 없습니다.

Tasks

Novel View Synthesis3D Reconstruction

Similar Papers 제목 키워드 기반

SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splatting

2025-03-31 · Advaith V. Sethuraman, Max Rucker, Onur Bagoren, Pou-Chun Kung 외

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 …

3D ReconstructionImage GenerationNovel View Synthesis

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

LEGS: Laplacian-Enhanced Gaussian Splatting with a Nonlinear Weighted Loss

2026-06-06 · Yongfei Guo, Qizhou Huo, Xuan Sun, Yuanhao Gong arxiv

3D Gaussian Splatting (3DGS) has become an efficient explicit representation for radiance field reconstruction and real-time novel view synthesis. However, its standard photometric loss treats flat and structure-rich reg…

Novel View Synthesis

Few-shot Novel View Synthesis using Depth Aware 3D Gaussian Splatting

2024-10-14 · Raja Kumar, Vanshika Vats

3D Gaussian splatting has surpassed neural radiance field methods in novel view synthesis by achieving lower computational costs and real-time high-quality rendering. Although it produces a high-quality rendering with a …

3DGSDepth EstimationDepth PredictionNovel View Synthesis

DisC-GS: Discontinuity-aware Gaussian Splatting

2024-05-24 · Haoxuan Qu, Zhuoling Li, Hossein Rahmani, Yujun Cai 외

Recently, Gaussian Splatting, a method that represents a 3D scene as a collection of Gaussian distributions, has gained significant attention in addressing the task of novel view synthesis. In this paper, we highlight a …

Novel View Synthesis