Street-View Image Generation from a Bird's-Eye View Layout

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Swerdlow, Alexander, Xu, Runsheng, Zhou, Bolei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910327827857408
author Swerdlow, Alexander
Xu, Runsheng
Zhou, Bolei
author_facet Swerdlow, Alexander
Xu, Runsheng
Zhou, Bolei
contents Bird's-Eye View (BEV) Perception has received increasing attention in recent years as it provides a concise and unified spatial representation across views and benefits a diverse set of downstream driving applications. At the same time, data-driven simulation for autonomous driving has been a focal point of recent research but with few approaches that are both fully data-driven and controllable. Instead of using perception data from real-life scenarios, an ideal model for simulation would generate realistic street-view images that align with a given HD map and traffic layout, a task that is critical for visualizing complex traffic scenarios and developing robust perception models for autonomous driving. In this paper, we propose BEVGen, a conditional generative model that synthesizes a set of realistic and spatially consistent surrounding images that match the BEV layout of a traffic scenario. BEVGen incorporates a novel cross-view transformation with spatial attention design which learns the relationship between cameras and map views to ensure their consistency. We evaluate the proposed model on the challenging NuScenes and Argoverse 2 datasets. After training, BEVGen can accurately render road and lane lines, as well as generate traffic scenes with diverse different weather conditions and times of day.
format Preprint
id arxiv_https___arxiv_org_abs_2301_04634
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Street-View Image Generation from a Bird's-Eye View Layout
Swerdlow, Alexander
Xu, Runsheng
Zhou, Bolei
Computer Vision and Pattern Recognition
Bird's-Eye View (BEV) Perception has received increasing attention in recent years as it provides a concise and unified spatial representation across views and benefits a diverse set of downstream driving applications. At the same time, data-driven simulation for autonomous driving has been a focal point of recent research but with few approaches that are both fully data-driven and controllable. Instead of using perception data from real-life scenarios, an ideal model for simulation would generate realistic street-view images that align with a given HD map and traffic layout, a task that is critical for visualizing complex traffic scenarios and developing robust perception models for autonomous driving. In this paper, we propose BEVGen, a conditional generative model that synthesizes a set of realistic and spatially consistent surrounding images that match the BEV layout of a traffic scenario. BEVGen incorporates a novel cross-view transformation with spatial attention design which learns the relationship between cameras and map views to ensure their consistency. We evaluate the proposed model on the challenging NuScenes and Argoverse 2 datasets. After training, BEVGen can accurately render road and lane lines, as well as generate traffic scenes with diverse different weather conditions and times of day.
title Street-View Image Generation from a Bird's-Eye View Layout
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2301.04634