PseudoMapTrainer: Learning Online Mapping without HD Maps

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Löwens, Christian, Funke, Thorben, Xie, Jingchao, Condurache, Alexandru Paul
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908503955734528
author Löwens, Christian
Funke, Thorben
Xie, Jingchao
Condurache, Alexandru Paul
author_facet Löwens, Christian
Funke, Thorben
Xie, Jingchao
Condurache, Alexandru Paul
contents Online mapping models show remarkable results in predicting vectorized maps from multi-view camera images only. However, all existing approaches still rely on ground-truth high-definition maps during training, which are expensive to obtain and often not geographically diverse enough for reliable generalization. In this work, we propose PseudoMapTrainer, a novel approach to online mapping that uses pseudo-labels generated from unlabeled sensor data. We derive those pseudo-labels by reconstructing the road surface from multi-camera imagery using Gaussian splatting and semantics of a pre-trained 2D segmentation network. In addition, we introduce a mask-aware assignment algorithm and loss function to handle partially masked pseudo-labels, allowing for the first time the training of online mapping models without any ground-truth maps. Furthermore, our pseudo-labels can be effectively used to pre-train an online model in a semi-supervised manner to leverage large-scale unlabeled crowdsourced data. The code is available at github.com/boschresearch/PseudoMapTrainer.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18788
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PseudoMapTrainer: Learning Online Mapping without HD Maps
Löwens, Christian
Funke, Thorben
Xie, Jingchao
Condurache, Alexandru Paul
Computer Vision and Pattern Recognition
Machine Learning
Robotics
Online mapping models show remarkable results in predicting vectorized maps from multi-view camera images only. However, all existing approaches still rely on ground-truth high-definition maps during training, which are expensive to obtain and often not geographically diverse enough for reliable generalization. In this work, we propose PseudoMapTrainer, a novel approach to online mapping that uses pseudo-labels generated from unlabeled sensor data. We derive those pseudo-labels by reconstructing the road surface from multi-camera imagery using Gaussian splatting and semantics of a pre-trained 2D segmentation network. In addition, we introduce a mask-aware assignment algorithm and loss function to handle partially masked pseudo-labels, allowing for the first time the training of online mapping models without any ground-truth maps. Furthermore, our pseudo-labels can be effectively used to pre-train an online model in a semi-supervised manner to leverage large-scale unlabeled crowdsourced data. The code is available at github.com/boschresearch/PseudoMapTrainer.
title PseudoMapTrainer: Learning Online Mapping without HD Maps
topic Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2508.18788