TICMapNet

A Tightly Coupled Temporal Fusion Pipeline for End-to-End HD Map Construction

Introduction

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

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

More Frames Results on the nuScenes validation dataset

Historical frames	Backbone	PV2BEV	BEVDeocder	Lr Schd	mAP	Config	Download
1	R50	GKT	DQ	24ep	59.0	config	model
2	R50	GKT	DQ	24ep	60.1	config	model
3	R50	GKT	DQ	24ep	61.3	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.

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.