TICMapNet

A Tightly Coupled Temporal Fusion Pipeline for Vectorized HD Map Learning

Introduction

TICMapNet is a simple and general temporal fusion pipeline designed for vectorized HD map construction.

Wenzhao Qiu¹,Shanmin Pang^{1 📧},Hao Zhang¹,Jianwu Fang¹,Jianru Xue¹

¹ Xi’an Jiaotong University

(^📧) corresponding author

accepted as RA-L

High-Definition (HD) map construction is essential for autonomous driving to accurately understand the surrounding environment. In this paper, we propose a Tightly Coupled temporal fusion Map Network (TICMapNet). TICMapNet breaks down the fusion process into three sub-problems: PV feature alignment, BEV feature adjustment, and Query feature fusion. By doing so, we effectively integrate temporal information at different stages through three plug-and-play modules, using the proposed tightly coupled strategy. Our approach does not rely on camera extrinsic parameters, offering a new perspective for addressing the visual fusion challenge in the field of object detection. Experimental results demonstrate that TICMapNet significantly enhances the single-frame baseline and achieves impressive performance across multiple datasets.

Getting Started

• Prepare Dataset
• Installization

Models

Results on the nuScenes validation dataset

Method	Backbone	PV2BEV	BEVDeocder	Lr Schd	mAP	Config	Download
ours_2	R50	GKT	DQ	24ep	59.0	config	model

Results on the OpenLane 300 validation dataset

Method	Backbone	PV2BEV	BEVDeocder	Lr Schd	mAP	Config	Download
ours_1	R50	GKT	VA	10ep	61.7	config	model
ours_2	R50	GKT	DQ	10ep	60.6	config	model

Results on the new nuScenes validation dataset

Method	Backbone	PV2BEV	BEVDeocder	Lr Schd	mAP	Config	Download
ours_2[1]	R50	GKT	DQ	24ep	28.3	config	model
ours_2[2]	R50	GKT	DQ	24ep	32.9	config	model

Results of TICMapNet_t on the nuScenes validation dataset

Method	Backbone	PV2BEV	BEVDeocder	Lr Schd	mAP	Config	Download
ours_2	R50	GKT	DQ	24ep	57.4	config	model

Results of TICMapNet_t on the OpenLane 300 validation dataset

Method	Backbone	PV2BEV	BEVDeocder	Lr Schd	mAP	Config	Download
ours_2	R50	GKT	VA	10ep	59.7	config	model

Notes:

ours_1 employs MapTR as a single-frame baseline, and ours_2 introduces Decoupled Query based on ours_1.

Qualitative results on nuScenes validation dataset and OpenLane 300 validation dataset

TICMapNet maintains stable and robust map construction quality in various driving scenes.

TICMapNet and TICMapNet_l visualization results on the nuScenes validation dataset.

Some failure cases on the new nuScenes validation dataset^[2]

[1]A. Lilja, J. Fu, E. Stenborg, and L. Hammarstrand, "Localization is all you evaluate: Data leakage in online mapping datasets and how to fix it," in CVPR 2024, pp. 22150–22159.

[2]T. Yuan, Y. Liu, Y. Wang, Y. Wang and H. Zhao, "StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction," in WACV 2024, pp. 7341-7350.

Qualitative results on self-collected dataset

TICMapNet maintains stable and robust map construction quality compared with the single baseline.

video

Acknowledgements

TICMapNet is based on MapTR. It is also greatly inspired by the following outstanding contributions to the open-source community:BEVFormer, StreamMapNet,BEVFusion,GKT,mmdetection3d.

Citation

If you find TICMapNet is useful in your research, please consider citing it by the following BibTeX entry.

@ARTICLE{10740793,
  author={Qiu, Wenzhao and Pang, Shanmin and Zhang, Hao and Fang, Jianwu and Xue, Jianru},
  journal={IEEE Robotics and Automation Letters}, 
  title={TICMapNet: A Tightly Coupled Temporal Fusion Pipeline for Vectorized HD Map Learning}, 
  year={2024},
  volume={},
  number={},
  pages={1-8},
  keywords={Feature extraction;History;Cameras;Object detection;Encoding;Three-dimensional displays;Decoding;Pipelines;Visualization;Manuals;Vectorized HD map;Temporal fusion},
  doi={10.1109/LRA.2024.3490384}}
}