Conference item icon

Conference item

PriorEye: geospatial visual priors for end-to-end autonomous driving

Abstract:

Most end-to-end autonomous driving methods rely solely on instantaneous sensor observations, limiting them to reactive behavior without the anticipatory foresight human drivers employ through prior experience. We introduce geospatial visual priors, street-level visual context anchored to the intended driving route, providing visual-spatial foresight independent of real-time sensors. We propose a memory augmentation module featuring a dual-memory architecture and an adaptive memory gate, which can be easily integrated into existing end-to-end approaches. This design pairs a contextual memory for retrieved priors with a persistent fallback memory, and dynamically regulates the influence of memories based on current state compatibility. Evaluated on the NAVSIM-v2 benchmark, our approach consistently improves performance across diverse end-to-end baselines. Furthermore, because these priors are independent of onboard sensors, our method inherently improves robustness against sensor corruption, while the dual-memory design ensures safe fallback when the retrieved priors themselves become unreliable. Our project page is available at https://orimrg.github.io/PriorEye.

Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.1007/978-3-032-37016-7_36

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Keble College
Role:
Author
ORCID:
0000-0001-6121-5839


Publisher:
European Computer Vision Association
Host title:
Computer Vision – ECCV 2026
Pages:
670-688
Series:
Lecture Notes in Computer Science
Series number:
17071
Publication date:
2026-09-12
Acceptance date:
2026-06-18
Event title:
19th European Conference on Computer Vision (ECCV 2026)
Event location:
Malmö, Sweden
Event website:
https://eccv.ecva.net/Conferences/2026
Event start date:
2026-09-08
Event end date:
2026-09-12
DOI:
EISSN:
1611-3349
ISSN:
0302-9743
EISBN:
9783032370167
ISBN:
9783032370150


Language:
English
Keywords:
Pubs id:
2439836
Local pid:
pubs:2439836
Deposit date:
2026-06-30
ARK identifier:

Terms of use


Views and Downloads

Views and downloads will return soon






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP