# Learning to Map Vehicles into Bird's Eye View

arXiv: https://arxiv.org/abs/1706.08442 · HTML: https://mlsanity.com/paper/1706.08442/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2017.

## Built on by (most cited first, 12 of 12)

- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [Translating Images into Maps](https://mlsanity.com/paper/2110.00966/) (2021)
- [Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images](https://mlsanity.com/paper/2108.03227/) (2021)
- [Local and Global GANs with Semantic-Aware Upsampling for Image Generation](https://mlsanity.com/paper/2203.00047/) (2022)
- [A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation](https://mlsanity.com/paper/2304.03650/) (2023)
- [BroadBEV: Collaborative LiDAR-camera Fusion for Broad-sighted Bird's Eye View Map Construction](https://mlsanity.com/paper/2309.11119/) (2023)
- [You Only Look Bottom-Up for Monocular 3D Object Detection](https://mlsanity.com/paper/2401.15319/) (2024)
- [Deep Perspective Transformation Based Vehicle Localization on Bird's Eye View](https://mlsanity.com/paper/2311.06796/) (2023)
- [Bird Eye-View to Street-View: A Survey](https://mlsanity.com/paper/2405.08961/) (2024)
- [Towards Compact Autonomous Driving Perception with Balanced Learning and Multi-sensor Fusion](https://mlsanity.com/paper/2606.02979/) (2026)
- [Safety-Oriented Trajectory Ranking from BEV Perception Outputs](https://mlsanity.com/paper/2610.14066/) (2026)

## Abstract (arXiv)

Awareness of the road scene is an essential component for both autonomous vehicles and Advances Driver Assistance Systems and is gaining importance both for the academia and car companies. This paper presents a way to learn a semantic-aware transformation which maps detections from a dashboard camera view onto a broader bird's eye occupancy map of the scene. To this end, a huge synthetic dataset featuring 1M couples of frames, taken from both car dashboard and bird's eye view, has been collected and automatically annotated. A deep-network is then trained to warp detections from the first to the second view. We demonstrate the effectiveness of our model against several baselines and observe that is able to generalize on real-world data despite having been trained solely on synthetic ones.