Crowd-sourced mapping offers a scalable alternative to creating maps using traditional survey vehicles. Yet, existing methods either rely on prior high-definition (HD) maps or neglect uncertainties in the map fusion. In this work, we present a complete pipeline for HD map generation using production vehicles equipped only with a monocular camera, consumer-grade GNSS, and IMU. Our approach includes on-cloud localization using lightweight standard-definition maps, on-vehicle mapping via an extended object trajectory (EOT) Poisson multi-Bernoulli (PMB) filter with Gibbs sampling, and on-cloud multi-drive optimization and Bayesian map fusion. We represent the lane lines using B-splines, where each B-spline is parameterized by a sequence of Gaussian distributed control points, and propose a novel Bayesian fusion framework for B-spline trajectories with differing density representation, enabling principled handling of uncertainties. We evaluate our proposed approach, B2F-Map, on large-scale real-world datasets collected across diverse driving conditions and demonstrate that our method is able to produce geometrically consistent lane-level maps.
Cite
@article{arxiv.2603.01673,
title = {B$^2$F-Map: Crowd-sourced Mapping with Bayesian B-spline Fusion},
author = {Yiping Xie and Yuxuan Xia and Erik Stenborg and Junsheng Fu and Axel Beauvisage and Gabriel E. Garcia and Tianyu Wu and Gustaf Hendeby},
journal= {arXiv preprint arXiv:2603.01673},
year = {2026}
}