融合激光雷达与高斯点云，实现更精确的三维重建与渲染。
GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction
- 用神经SDF引导高斯点初始化，提升几何合理性
- 在多轨迹测试中重建精度显著优于现有方法
- 适合自动驾驶与数字孪生场景的高保真建模
数字孪生是自动驾驶和具身人工智能发展的基础，但实现高粒度表面重建与高保真渲染仍具挑战。高斯点云虽能高效渲染逼真图像，但在机器人应用中因原始点碎片化和观测数据稀疏，常出现几何不一致问题。现有依赖渲染结果约束的正则化方法在复杂环境中表现不佳。同时，如何有效融合稀疏激光雷达（LiDAR）数据与高斯点云仍是一大难题。本文提出统一的激光雷达-视觉系统，将高斯点云与神经符号距离场（neural SDF）相结合。精确的激光雷达点云可训练出连续的流形几何场，进而为高斯点提供基于物理的地基初始化，并引入全面的几何正则化以实现几何一致的渲染与重建。实验表明，在多种轨迹下均取得更优的重建精度与渲染质量。代码已开源：https://github.com/hku-mars/GS-SDF。
原文摘要 · Abstract (English)
Digital twins are fundamental to the development of autonomous driving and embodied artificial intelligence. However, achieving high-granularity surface reconstruction and high-fidelity rendering remains a challenge. Gaussian splatting offers efficient photorealistic rendering but struggles with geometric inconsistencies due to fragmented primitives and sparse observational data in robotics applications. Existing regularization methods, which rely on render-derived constraints, often fail in complex environments. Moreover, effectively integrating sparse LiDAR data with Gaussian splatting remains challenging. We propose a unified LiDAR-visual system that synergizes Gaussian splatting with a neural signed distance field. The accurate LiDAR point clouds enable a trained neural signed distance field to offer a manifold geometry field. This motivates us to offer an SDF-based Gaussian initialization for physically grounded primitive placement and a comprehensive geometric regularization for geometrically consistent rendering and reconstruction. Experiments demonstrate superior reconstruction accuracy and rendering quality across diverse trajectories. To benefit the community, the codes are released at https://github.com/hku-mars/GS-SDF.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。