MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation
Xiaoshuai Hao, Ruikai Li, Hui Zhang, Dingzhe Li, Rong Yin, Sangil, Jung, Seung-In Park, ByungIn Yoo, Haimei Zhao, Jing Zhang

TL;DR
MapDistill introduces a novel knowledge distillation framework that transfers knowledge from a camera-LiDAR fusion model to a lightweight camera-only model, significantly improving HD map construction efficiency and accuracy in autonomous driving.
Contribution
The paper proposes the first KD-based approach for HD map construction, employing a dual BEV transform and comprehensive distillation schemes to enable cost-effective camera-only models to outperform existing methods.
Findings
Surpasses existing methods by over 7.7 mAP on nuScenes
Achieves 4.5 times speedup in HD map construction
Effectively transfers knowledge from fusion to camera-only models
Abstract
Online high-definition (HD) map construction is an important and challenging task in autonomous driving. Recently, there has been a growing interest in cost-effective multi-view camera-based methods without relying on other sensors like LiDAR. However, these methods suffer from a lack of explicit depth information, necessitating the use of large models to achieve satisfactory performance. To address this, we employ the Knowledge Distillation (KD) idea for efficient HD map construction for the first time and introduce a novel KD-based approach called MapDistill to transfer knowledge from a high-performance camera-LiDAR fusion model to a lightweight camera-only model. Specifically, we adopt the teacher-student architecture, i.e., a camera-LiDAR fusion model as the teacher and a lightweight camera model as the student, and devise a dual BEV transform module to facilitate cross-modal…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSatellite Image Processing and Photogrammetry · Robotics and Sensor-Based Localization · Advanced Vision and Imaging
MethodsKnowledge Distillation
