MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917815004430336 |
|---|---|
| author | Liao, Bencheng Chen, Shaoyu Zhang, Yunchi Jiang, Bo Zhang, Qian Liu, Wenyu Huang, Chang Wang, Xinggang |
| author_facet | Liao, Bencheng Chen, Shaoyu Zhang, Yunchi Jiang, Bo Zhang, Qian Liu, Wenyu Huang, Chang Wang, Xinggang |
| contents | High-definition (HD) map provides abundant and precise static environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system. In this paper, we present \textbf{Map} \textbf{TR}ansformer, an end-to-end framework for online vectorized HD map construction. We propose a unified permutation-equivalent modeling approach, \ie, modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process. We design a hierarchical query embedding scheme to flexibly encode structured map information and perform hierarchical bipartite matching for map element learning. To speed up convergence, we further introduce auxiliary one-to-many matching and dense supervision. The proposed method well copes with various map elements with arbitrary shapes. It runs at real-time inference speed and achieves state-of-the-art performance on both nuScenes and Argoverse2 datasets. Abundant qualitative results show stable and robust map construction quality in complex and various driving scenes. Code and more demos are available at \url{https://github.com/hustvl/MapTR} for facilitating further studies and applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_05736 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction Liao, Bencheng Chen, Shaoyu Zhang, Yunchi Jiang, Bo Zhang, Qian Liu, Wenyu Huang, Chang Wang, Xinggang Computer Vision and Pattern Recognition Robotics High-definition (HD) map provides abundant and precise static environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system. In this paper, we present \textbf{Map} \textbf{TR}ansformer, an end-to-end framework for online vectorized HD map construction. We propose a unified permutation-equivalent modeling approach, \ie, modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process. We design a hierarchical query embedding scheme to flexibly encode structured map information and perform hierarchical bipartite matching for map element learning. To speed up convergence, we further introduce auxiliary one-to-many matching and dense supervision. The proposed method well copes with various map elements with arbitrary shapes. It runs at real-time inference speed and achieves state-of-the-art performance on both nuScenes and Argoverse2 datasets. Abundant qualitative results show stable and robust map construction quality in complex and various driving scenes. Code and more demos are available at \url{https://github.com/hustvl/MapTR} for facilitating further studies and applications. |
| title | MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2308.05736 |