HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps

Lu Mi, Hang Zhao, Charlie Nash, Xiaohan Jin, Jiyang Gao, Chen Sun, Cordelia Schmid, Nir Shavit, Yuning Chai, Dragomir Anguelov; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 4227-4236

Abstract


High Definition (HD) maps are maps with precise definitions of road lanes with rich semantics of the traffic rules. They are critical for several key stages in an autonomous driving system, including motion forecasting and planning. However, there are only a small amount of real-world road topologies and geometries, which significantly limits our ability to test out the self-driving stack to generalize onto new unseen scenarios. To address this issue, we introduce a new challenging task to generate HD maps. In this work, we explore several autoregressive models using different data representations, including sequence, plain graph, and hierarchical graph. We propose HDMapGen, a hierarchical graph generation model capable of producing high-quality and diverse HD maps through a coarse-to-fine approach. Experiments on the Argoverse dataset and an in-house dataset show that HDMapGen significantly outperforms baseline methods. Additionally, we demonstrate that HDMapGen achieves high efficiency and scalability.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Mi_2021_CVPR, author = {Mi, Lu and Zhao, Hang and Nash, Charlie and Jin, Xiaohan and Gao, Jiyang and Sun, Chen and Schmid, Cordelia and Shavit, Nir and Chai, Yuning and Anguelov, Dragomir}, title = {HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {4227-4236} }