GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction

作者：Jianheng Liu, Yunfei Wan, Bowen Wang, Chunran Zheng, Jiarong Lin, Fu Zhang · 年份：2025 · DOI：10.1109/iros60139.2025.11246239 · 被引用次数：2 · 研究领域：3D Shape Modeling and Analysis、Computer Graphics and Visualization Techniques、Robotics and Sensor-Based Localization

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.