PseudoMapTrainer: Learning Online Mapping without HD Maps

TL;DR

PseudoMapTrainer introduces a method for online mapping that trains without high-definition maps by generating pseudo-labels from unlabeled sensor data, enabling scalable and diverse map learning.

Contribution

It presents a novel pseudo-label generation and training approach that eliminates the need for ground-truth HD maps in online mapping models.

Findings

Effective pseudo-labels enable training without ground-truth maps

Semi-supervised pre-training improves model performance

First method to train online mapping models without HD maps

Abstract

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.