An Initial Study of Bird's-Eye View Generation for Autonomous Vehicles using Cross-View Transformers

Felipe Carlos dos Santos, Eric Aislan Antonelo, Gustavo Claudio Karl Couto
8/17/2025
cs.CVcs.AI

No confident code implementation found for this paper. 1 possible match can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

GenMapping: Unleashing the Potential of Inverse Perspective Mapping for Robust Online HD Map Construction

85% match1 repo142024

A Benchmark for Vision-Centric HD Mapping by V2I Systems

84% match2025

OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping

84% match1 repo342024

RopeBEV: A Multi-Camera Roadside Perception Network in Bird's-Eye-View

83% match2024

An Examination of Offline-Trained Encoders in Vision-Based Deep Reinforcement Learning for Autonomous Driving

83% match2024

Learning autonomous driving from aerial imagery

83% match2024

Cite this paper

@article{santos2025initial,
  title  = {An Initial Study of Bird's-Eye View Generation for Autonomous Vehicles using Cross-View Transformers},
  author = {Felipe Carlos dos Santos and Eric Aislan Antonelo and Gustavo Claudio Karl Couto},
  year   = {2025},
  eprint = {2508.12520},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.12520v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.12520.svg)](https://codeofpaper.com/paper/2508.12520)

Discussion