G2-SDF: Geometry-Guided Neural Signed Distance Fields for Scalable and Detailed Reconstruction

Efficient reconstruction methods, particularly capable of providing detailed information on obstacle distances across diverse environments, are crucial for effective robot motion planning. In this context, neural Signed Distance Fields (SDFs) offer a powerful solution by learning implicit representations of environments, enabling fast and precise distance queries to obstacles. In this work, we introduce G2-SDF, a method designed to achieve scalable and detailed reconstruction of environments while ensuring high training efficiency. In particular, our approach utilizes a precise normal direction sampling strategy, which incorporates a rapid normal estimation technique to compute accurate boundaries along surface normals. This effectively filters out erroneous samples and enhances SDF accuracy. To mitigate catastrophic forgetting in incremental learning scenarios, we propose a fine-grained voxel sliding window method that efficiently manages historical data while optimizing video memory usage. Subsequently, we partition feature areas based on the calculated normal boundaries and implement an importance sampling strategy that emphasizes capturing detailed regions. We evaluate G2-SDF on both indoor (Replica and ScanNet) and outdoor (Maicity and Newer College Quad) datasets. Our method surpasses existing approaches and achieves superior reconstruction accuracy while maintaining high efficiency in scalable environments.