An Initial Study of Bird’s-Eye View Generation for Autonomous Vehicles using Cross-View Transformers
- 29 September 2025
- conference paper
- Published by Sociedade Brasileira de Computação
- p. 855-866
Abstract
Bird’s-Eye View (BEV) maps provide a structured, top-down abstraction that is crucial for autonomous-driving perception. In this work, we employ Cross-View Transformers (CVT) for learning to map camera images to three BEV’s channels - road, lane markings, and planned trajectory - using a realistic simulator for urban driving. Our study examines generalization to unseen towns, the effect of different camera layouts, and two loss formulations (focal and L1). Using training data from only a town, a four-camera CVT trained with the L1 loss delivers the most robust test performance, evaluated in a new town. Overall, our results underscore CVT’s promise for mapping camera inputs to reasonably accurate BEV maps.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Investigating Behavior Cloning from Few Demonstrations for Autonomous Driving Based on Bird’s-Eye View in Simulated Cities2025
- CoBEVFusion Cooperative Perception with LiDAR-Camera Bird's Eye View Fusion2024
- FIERY: Future Instance Prediction in Bird’s-Eye View from Surround Monocular Cameras2021
- V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction2020
- Cross-View Semantic Segmentation for Sensing SurroundingsIEEE Robotics and Automation Letters, 2020
- End-to-End Driving Via Conditional Imitation Learning2018
- Focal Loss for Dense Object Detection2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015