MapFusion: A General Framework for 3D Object Detection with HDMaps

TL;DR

MapFusion is a versatile framework that enhances 3D object detection in autonomous driving by effectively integrating High Definition Map data into various detection pipelines, leading to significant accuracy improvements.

Contribution

The paper introduces MapFusion, a detector-independent framework that fuses HD map features into 3D object detection models, improving their performance.

Findings

Achieved 1.27 to 2.79 points mAP improvements across three baselines.

Demonstrated effectiveness on large public autonomous driving datasets.

Framework is simple, effective, and easily integrable into existing detectors.

Abstract

3D object detection is a key perception component in autonomous driving. Most recent approaches are based on Lidar sensors only or fused with cameras. Maps (e.g., High Definition Maps), a basic infrastructure for intelligent vehicles, however, have not been well exploited for boosting object detection tasks. In this paper, we propose a simple but effective framework - MapFusion to integrate the map information into modern 3D object detector pipelines. In particular, we design a FeatureAgg module for HD Map feature extraction and fusion, and a MapSeg module as an auxiliary segmentation head for the detection backbone. Our proposed MapFusion is detector independent and can be easily integrated into different detectors. The experimental results of three different baselines on large public autonomous driving dataset demonstrate the superiority of the proposed framework. By fusing the map information, we can achieve 1.27 to 2.79 points improvements for mean Average Precision (mAP) on three strong 3d object detection baselines.