RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation
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_ | 1866929392497721344 |
|---|---|
| author | Mei, Ruohong Sui, Wei Zhang, Jiaxin Qin, Xue Wang, Gang Peng, Tao Yang, Cong |
| author_facet | Mei, Ruohong Sui, Wei Zhang, Jiaxin Qin, Xue Wang, Gang Peng, Tao Yang, Cong |
| contents | In autonomous driving applications, accurate and efficient road surface reconstruction is paramount. This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces. Leveraging a unique mesh representation, RoMe ensures that the reconstructed road surfaces are accurate and seamlessly aligned with semantics. To address challenges in computational efficiency, we propose a waypoint sampling strategy, enabling RoMe to reconstruct vast environments by focusing on sub-areas and subsequently merging them. Furthermore, we incorporate an extrinsic optimization module to enhance the robustness against inaccuracies in extrinsic calibration. Our extensive evaluations of both public datasets and wild data underscore RoMe's superiority in terms of speed, accuracy, and robustness. For instance, it costs only 2 GPU hours to recover a road surface of 600*600 square meters from thousands of images. Notably, RoMe's capability extends beyond mere reconstruction, offering significant value for autolabeling tasks in autonomous driving applications. All related data and code are available at https://github.com/DRosemei/RoMe. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_11368 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation Mei, Ruohong Sui, Wei Zhang, Jiaxin Qin, Xue Wang, Gang Peng, Tao Yang, Cong Computer Vision and Pattern Recognition In autonomous driving applications, accurate and efficient road surface reconstruction is paramount. This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces. Leveraging a unique mesh representation, RoMe ensures that the reconstructed road surfaces are accurate and seamlessly aligned with semantics. To address challenges in computational efficiency, we propose a waypoint sampling strategy, enabling RoMe to reconstruct vast environments by focusing on sub-areas and subsequently merging them. Furthermore, we incorporate an extrinsic optimization module to enhance the robustness against inaccuracies in extrinsic calibration. Our extensive evaluations of both public datasets and wild data underscore RoMe's superiority in terms of speed, accuracy, and robustness. For instance, it costs only 2 GPU hours to recover a road surface of 600*600 square meters from thousands of images. Notably, RoMe's capability extends beyond mere reconstruction, offering significant value for autolabeling tasks in autonomous driving applications. All related data and code are available at https://github.com/DRosemei/RoMe. |
| title | RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2306.11368 |