Research papers · 2025.05

Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving

Benchmarking and Improving Bird’s Eye View Perception Robustness in Autonomous Driving

Overview

RoboBEV benchmarks BEV perception across camera corruptions and sensor failures. The study compares multiple tasks and models, analyzing pretraining, temporal information and a CLIP-based enhancement for out-of-distribution robustness.

Author-supplied source information

Author-supplied information on arXiv.

TPAMI 2025; 17 pages, 13 figures, 11 tables; Code at this https URL: https://github.com/Daniel-xsy/RoboBEV

Version: arXiv v2 — manuscript revision

PARTICIPATION ENQUIRY

Participation enquiry

Your enquiry will be delivered by email. We will reply to the address you provide.

Email enquiries: info@battermachine.com