HeightMapNet: Explicit Height Modeling for End-to-End HD Map Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929574630129664 |
|---|---|
| author | Qiu, Wenzhao Pang, Shanmin zhang, Hao Fang, Jianwu Xue, Jianru |
| author_facet | Qiu, Wenzhao Pang, Shanmin zhang, Hao Fang, Jianwu Xue, Jianru |
| contents | Recent advances in high-definition (HD) map construction from surround-view images have highlighted their cost-effectiveness in deployment. However, prevailing techniques often fall short in accurately extracting and utilizing road features, as well as in the implementation of view transformation. In response, we introduce HeightMapNet, a novel framework that establishes a dynamic relationship between image features and road surface height distributions. By integrating height priors, our approach refines the accuracy of Bird's-Eye-View (BEV) features beyond conventional methods. HeightMapNet also introduces a foreground-background separation network that sharply distinguishes between critical road elements and extraneous background components, enabling precise focus on detailed road micro-features. Additionally, our method leverages multi-scale features within the BEV space, optimally utilizing spatial geometric information to boost model performance. HeightMapNet has shown exceptional results on the challenging nuScenes and Argoverse 2 datasets, outperforming several widely recognized approaches. The code will be available at \url{https://github.com/adasfag/HeightMapNet/}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_01408 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HeightMapNet: Explicit Height Modeling for End-to-End HD Map Learning Qiu, Wenzhao Pang, Shanmin zhang, Hao Fang, Jianwu Xue, Jianru Computer Vision and Pattern Recognition Artificial Intelligence Recent advances in high-definition (HD) map construction from surround-view images have highlighted their cost-effectiveness in deployment. However, prevailing techniques often fall short in accurately extracting and utilizing road features, as well as in the implementation of view transformation. In response, we introduce HeightMapNet, a novel framework that establishes a dynamic relationship between image features and road surface height distributions. By integrating height priors, our approach refines the accuracy of Bird's-Eye-View (BEV) features beyond conventional methods. HeightMapNet also introduces a foreground-background separation network that sharply distinguishes between critical road elements and extraneous background components, enabling precise focus on detailed road micro-features. Additionally, our method leverages multi-scale features within the BEV space, optimally utilizing spatial geometric information to boost model performance. HeightMapNet has shown exceptional results on the challenging nuScenes and Argoverse 2 datasets, outperforming several widely recognized approaches. The code will be available at \url{https://github.com/adasfag/HeightMapNet/}. |
| title | HeightMapNet: Explicit Height Modeling for End-to-End HD Map Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2411.01408 |