Paper

Learning Ego-Centric BEV Representations from a Perspective-Privileged View: Cross-View Supervision for Online HD Map Construction

Bogenberger, Klaus, Lengerer, Daniel, Pechinger, Mathias, Markgraf, Carsten

2026

Overview

Bird's-eye-view (BEV) representations derived from multi-camera input have become a central interface for online high-definition (HD) map construction. However, most approaches rely solely on ego-centric supervision, requiring large-scale scene structure to be inferred from incomplete observations, occlusions, and diminishing information density at long range, where perspective effects and spatial sparsity hinder consistent structural reasoning. We introduce Cross-View Supervision (CVS), a representation learning paradigm that transfers geometric and topological priors from an ego-aligned overhead perspective into camera-based BEV encoders. Rather than adding auxiliary semantic losses, CVS aligns representations in a shared BEV feature space and distills globally consistent structural knowledge from a perspective-privileged teacher into the ego-centric backbone. This supervision enhances structural coherence without modifying the inference architecture or requiring overhead input at test time. Experiments on nuScenes using ego-aligned aerial imagery from the AID4AD cross-view extension demonstrate consistent improvements over StreamMapNet while maintaining identical camera-only inference. CVS yields +3.9\\,mAP in the standard \\(6030\\,m\\) region and +9.9\\,mAP in the extended \\(10050\\,m\\) setting, corresponding to a 44\\% relative gain at long range. These results highlight perspective-privileged structural supervision as a promising training principle for improving BEV representation learning in HD map construction.

• Publisher: Cornell University Library, arXiv.org
• Subject: Cameras / High definition / Inference / Representation learning / Supervision