V2VSSC: A 3D Semantic Scene Completion Benchmark for Perception with Vehicle to Vehicle Communication
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914670045036544 |
|---|---|
| author | Zhang, Yuanfang Li, Junxuan Luo, Kaiqing Yang, Yiying Han, Jiayi Liu, Nian Qin, Denghui Han, Peng Xu, Chengpei |
| author_facet | Zhang, Yuanfang Li, Junxuan Luo, Kaiqing Yang, Yiying Han, Jiayi Liu, Nian Qin, Denghui Han, Peng Xu, Chengpei |
| contents | Semantic scene completion (SSC) has recently gained popularity because it can provide both semantic and geometric information that can be used directly for autonomous vehicle navigation. However, there are still challenges to overcome. SSC is often hampered by occlusion and short-range perception due to sensor limitations, which can pose safety risks. This paper proposes a fundamental solution to this problem by leveraging vehicle-to-vehicle (V2V) communication. We propose the first generalized collaborative SSC framework that allows autonomous vehicles to share sensing information from different sensor views to jointly perform SSC tasks. To validate the proposed framework, we further build V2VSSC, the first V2V SSC benchmark, on top of the large-scale V2V perception dataset OPV2V. Extensive experiments demonstrate that by leveraging V2V communication, the SSC performance can be increased by 8.3% on geometric metric IoU and 6.0% mIOU. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_04671 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | V2VSSC: A 3D Semantic Scene Completion Benchmark for Perception with Vehicle to Vehicle Communication Zhang, Yuanfang Li, Junxuan Luo, Kaiqing Yang, Yiying Han, Jiayi Liu, Nian Qin, Denghui Han, Peng Xu, Chengpei Computer Vision and Pattern Recognition Semantic scene completion (SSC) has recently gained popularity because it can provide both semantic and geometric information that can be used directly for autonomous vehicle navigation. However, there are still challenges to overcome. SSC is often hampered by occlusion and short-range perception due to sensor limitations, which can pose safety risks. This paper proposes a fundamental solution to this problem by leveraging vehicle-to-vehicle (V2V) communication. We propose the first generalized collaborative SSC framework that allows autonomous vehicles to share sensing information from different sensor views to jointly perform SSC tasks. To validate the proposed framework, we further build V2VSSC, the first V2V SSC benchmark, on top of the large-scale V2V perception dataset OPV2V. Extensive experiments demonstrate that by leveraging V2V communication, the SSC performance can be increased by 8.3% on geometric metric IoU and 6.0% mIOU. |
| title | V2VSSC: A 3D Semantic Scene Completion Benchmark for Perception with Vehicle to Vehicle Communication |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.04671 |