Enregistré dans:
Détails bibliographiques
Auteurs principaux: Niemeijer, Joshua, Zekri, Alaa Eddine Ben, Bahmanyar, Reza, Schmälzle, Philipp M., Chaabouni-Chouayakh, Houda, Kurz, Franz
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.19411
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914494997856256
author Niemeijer, Joshua
Zekri, Alaa Eddine Ben
Bahmanyar, Reza
Schmälzle, Philipp M.
Chaabouni-Chouayakh, Houda
Kurz, Franz
author_facet Niemeijer, Joshua
Zekri, Alaa Eddine Ben
Bahmanyar, Reza
Schmälzle, Philipp M.
Chaabouni-Chouayakh, Houda
Kurz, Franz
contents Understanding road scenes in a geometrically consistent, scene-centric representation is crucial for planning and mapping. We present GOLD-BEV, a framework that learns dense bird's-eye-view (BEV) semantic environment maps-including dynamic agents-from ego-centric sensors, using time-synchronized aerial imagery as supervision only during training. BEV-aligned aerial crops provide an intuitive target space, enabling dense semantic annotation with minimal manual effort and avoiding the ambiguity of ego-only BEV labeling. Crucially, strict aerial-ground synchronization allows overhead observations to supervise moving traffic participants and mitigates the temporal inconsistencies inherent to non-synchronized overhead sources. To obtain scalable dense targets, we generate BEV pseudo-labels using domain-adapted aerial teachers, and jointly train BEV segmentation with optional pseudo-aerial BEV reconstruction for interpretability. Finally, we extend beyond aerial coverage by learning to synthesize pseudo-aerial BEV images from ego sensors, which support lightweight human annotation and uncertainty-aware pseudo-labeling on unlabeled drives.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19411
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GOLD-BEV: GrOund and aeriaL Data for Dense Semantic BEV Mapping of Dynamic Scenes
Niemeijer, Joshua
Zekri, Alaa Eddine Ben
Bahmanyar, Reza
Schmälzle, Philipp M.
Chaabouni-Chouayakh, Houda
Kurz, Franz
Computer Vision and Pattern Recognition
Artificial Intelligence
Understanding road scenes in a geometrically consistent, scene-centric representation is crucial for planning and mapping. We present GOLD-BEV, a framework that learns dense bird's-eye-view (BEV) semantic environment maps-including dynamic agents-from ego-centric sensors, using time-synchronized aerial imagery as supervision only during training. BEV-aligned aerial crops provide an intuitive target space, enabling dense semantic annotation with minimal manual effort and avoiding the ambiguity of ego-only BEV labeling. Crucially, strict aerial-ground synchronization allows overhead observations to supervise moving traffic participants and mitigates the temporal inconsistencies inherent to non-synchronized overhead sources. To obtain scalable dense targets, we generate BEV pseudo-labels using domain-adapted aerial teachers, and jointly train BEV segmentation with optional pseudo-aerial BEV reconstruction for interpretability. Finally, we extend beyond aerial coverage by learning to synthesize pseudo-aerial BEV images from ego sensors, which support lightweight human annotation and uncertainty-aware pseudo-labeling on unlabeled drives.
title GOLD-BEV: GrOund and aeriaL Data for Dense Semantic BEV Mapping of Dynamic Scenes
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.19411