3D Perception with Differentiable Map Priors
Keywords: autonomous driving, 3D object detection, mapping
TL;DR: DMP enhances multi-view vision models with historical features that are learned end-to-end and stored in an efficient and scalable representation
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.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 12684
Loading