Exploring Semi-Supervised Learning for Online Mapping

A Lilja, E Wallin, J Fu, L Hammarstrand - arXiv preprint arXiv:2410.10279, 2024 - arxiv.org
Online mapping is important for scaling autonomous driving beyond well-defined areas.
Training a model to produce a local map, including lane markers, road edges, and …

PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentation

H Ishikawa, T Iida, Y Konishi, Y Aoki - arXiv preprint arXiv:2403.12530, 2024 - arxiv.org
Generating annotations for bird's-eye-view (BEV) segmentation presents significant
challenges due to the scenes' complexity and the high manual annotation cost. In this work …