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

arXiv: https://arxiv.org/abs/2605.12218 · HTML: https://mlsanity.com/paper/2605.12218/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 46 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection](https://mlsanity.com/paper/2203.17054/) (2022)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.11926/) (2023)
- [MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2208.14437/) (2022)
- [HDMapNet: An Online HD Map Construction and Evaluation Framework](https://mlsanity.com/paper/2107.06307/) (2021)
- [VectorMapNet: End-to-end Vectorized HD Map Learning](https://mlsanity.com/paper/2206.08920/) (2022)
- [ResUNet++: An Advanced Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1911.07067/) (2019)
- [MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2308.05736/) (2023)
- [Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks](https://mlsanity.com/paper/2003.13402/) (2020)
- [StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction](https://mlsanity.com/paper/2308.12570/) (2023)
- [RoadTracer: Automatic Extraction of Road Networks from Aerial Images](https://mlsanity.com/paper/1802.03680/) (2018)
- [End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve](https://mlsanity.com/paper/2306.09700/) (2023)
- [One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation](https://mlsanity.com/paper/2310.19444/) (2023)
- [MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping](https://mlsanity.com/paper/2403.15951/) (2024)
- [Sat2Graph: Road Graph Extraction through Graph-Tensor Encoding](https://mlsanity.com/paper/2007.09547/) (2020)
- [MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2404.00876/) (2024)
- [Stream Query Denoising for Vectorized HD Map Construction](https://mlsanity.com/paper/2401.09112/) (2024)
- [DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation](https://mlsanity.com/paper/2309.15109/) (2023)
- [DiffBEV: Conditional Diffusion Model for Bird's Eye View Perception](https://mlsanity.com/paper/2303.08333/) (2023)
- [MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation](https://mlsanity.com/paper/2407.11682/) (2024)
- [Mask2Map: Vectorized HD Map Construction Using Bird's Eye View Segmentation Masks](https://mlsanity.com/paper/2407.13517/) (2024)
- [DifFUSER: Diffusion Model for Robust Multi-Sensor Fusion in 3D Object Detection and BEV Segmentation](https://mlsanity.com/paper/2404.04629/) (2024)

## Built on by (most cited first, 1 of 1)

- [AerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion](https://mlsanity.com/paper/2606.24784/) (2026)

## Abstract (arXiv)

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 +3.9mAP in the standard 60×30,m region and +9.9mAP in the extended 100×50,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.