3D Perception with Differentiable Map Priors

Brady Zhou, Philipp KraehenbuehlOpenReview 2025 · Submission to ICLR 2025 · Rejected · OpenReview

Abstract

Human drivers rarely navigate where no person has gone before. After all, thousands of drivers use busy city roads every day, and only one can claim to be the first. The same holds for autonomous computer vision systems. The vast majority of the deployment area of an autonomous vision system will have been visited before. Yet, most computer vision systems act as if they are encountering each location for the first time. In this work, we present Differentiable Map Priors, a simple but effective framework to learn spatial priors from historic traversals. Differentiable Map Priors easily integrate into leading 3D perception systems at little to no extra computational costs. We show that they lead to a significant and consistent improvement in 3D object detection and semantic map segmentation tasks on the nuScenes dataset across several architectures.
BibTeX
@misc{zhou2025d,
  author = {Brady Zhou and Philipp Kraehenbuehl},
  title = {{3D Perception with Differentiable Map Priors}},
  year = {2025},
  url = {https://openreview.net/forum?id=KyqtKhv6q1},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2025},
}
Figure