LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection

arXiv:2206.07705v2 Announce Type: replace
Abstract: The 3D Average Precision (3D AP) relies on the intersection over union between predictions and ground truth objects. However, camera-only detectors have limited depth accuracy, which may cause otherwise reasonable predictions that suffer from such longitudinal localization errors to be treated as false positives. We therefore propose variants of the 3D AP metric to be more permissive with respect to depth estimation errors. Specifically, our novel longitudinal error tolerant metrics, LET-3D-AP and LET-3D-APL, allow longitudinal …

abstract accuracy arxiv cs.cv detection detectors error errors false false positives however intersection localization objects precision predictions truth type union