GS-SDF: LiDAR拡張ガウシアンスプラッティングとニューラルSDFによる幾何学的に一貫したレンダリングと再構成
GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction
LiDAR点群とニューラル符号付距離場(SDF)をガウシアンスプラッティングに統合し、幾何学的に一貫した高精度な表面再構成と高忠実度レンダリングを実現する手法を提案した。
著者: Jianheng Liu, Yunfei Wan, Bowen Wang, Chunran Zheng, Jiarong Lin, Fu Zhang
分類: cs.RO, cs.CV
原文アブストラクト
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.
