Year: 2025
Type: article
Abstract: Evaluating massive-scale point cloud maps in Simultaneous Localization and Mapping (SLAM) still remains challenging due to three limitations: lack of unified standards, poor robustness to noise, and computational inefficiency. We propose MapEval, a novel framework for point cloud map assessment. Our key innovation is a voxelized Gaussian approximation method that enables efficient Wasserstein distance computation while maintaining physical meaning. This leads to two complementary metrics: Voxelized Average Wasserstein Distance (AWD) for global geometry and Spatial Consistency Score (SCS) for local consistency. Extensive experiments demonstrate that MapEval achieves$100$-$500$times speedup while maintaining evaluation performance compared to traditional metrics like Chamfer Distance (CD) and Mean Map Entropy (MME). Our framework shows robust performance across both simulated and real-world datasets with million-scale point clouds.
Authors: Xiangcheng Hu, Jin Wu, Mingkai Jia, Hongyu Yan, Yi Jiang, Binqian Jiang, Wei Zhang, Wei He, Ping Tan
Language: English
Subfield: Aerospace Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4408254147