Compressed Map Priors for 3D Perception

2025-12-31

arXiv.org

AI Summary

Current autonomous driving vision systems treat perception in known areas as if encountering them for the first time, thereby neglecting valuable spatial priors embedded in historical traversal data. To address this limitation, this work proposes a lightweight framework that efficiently compresses and leverages historical spatial priors through a binary hash map structure—requiring only 32 KB per square kilometer—thus enhancing 3D perception with minimal storage and computational overhead. The method supports end-to-end training and integrates seamlessly into mainstream 3D detection architectures. Extensive experiments on the nuScenes dataset demonstrate consistent and significant performance improvements across multiple detection models, confirming the approach’s effectiveness and generalizability.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Human drivers rarely travel 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 autonomous vehicle vision systems act as if they are encountering each location for the first time. In this work, we present Compressed Map Priors (CMP), a simple but effective framework to learn spatial priors from historic traversals. The map priors use a binarized hashmap that requires only $32\text{KB}/\text{km}^2$, a $20\times$ reduction compared to the dense storage. Compressed Map Priors easily integrate into leading 3D perception systems at little to no extra computational costs, and lead to a significant and consistent improvement in 3D object detection on the nuScenes dataset across several architectures.

Problem

• 3D perception
• spatial priors
• autonomous driving
• map priors
• object detection

Innovation

• Compressed Map Priors
• spatial priors
• 3D object detection
• binary hashmap
• autonomous driving