Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917973439021056 |
|---|---|
| author | Wu, Chaofan Li, Jiaheng Cao, Jinghao Li, Ming Feng, Yongkang Xu, Jiayu Wu Shuwen Gao, Zihang Du, Sidan Li, Yang |
| author_facet | Wu, Chaofan Li, Jiaheng Cao, Jinghao Li, Ming Feng, Yongkang Xu, Jiayu Wu Shuwen Gao, Zihang Du, Sidan Li, Yang |
| contents | Accurate 3D perception is essential for autonomous driving. Traditional methods often struggle with geometric ambiguity due to a lack of geometric prior. To address these challenges, we use omnidirectional depth estimation to introduce geometric prior. Based on the depth information, we propose a Sketch-Coloring framework OmniDepth-Occ. Additionally, our approach introduces a cylindrical voxel representation based on polar coordinate to better align with the radial nature of panoramic camera views. To address the lack of fisheye camera dataset in autonomous driving tasks, we also build a virtual scene dataset with six fisheye cameras, and the data volume has reached twice that of SemanticKITTI. Experimental results demonstrate that our Sketch-Coloring network significantly enhances 3D perception performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01023 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving Wu, Chaofan Li, Jiaheng Cao, Jinghao Li, Ming Feng, Yongkang Xu, Jiayu Wu Shuwen Gao, Zihang Du, Sidan Li, Yang Computer Vision and Pattern Recognition Robotics Accurate 3D perception is essential for autonomous driving. Traditional methods often struggle with geometric ambiguity due to a lack of geometric prior. To address these challenges, we use omnidirectional depth estimation to introduce geometric prior. Based on the depth information, we propose a Sketch-Coloring framework OmniDepth-Occ. Additionally, our approach introduces a cylindrical voxel representation based on polar coordinate to better align with the radial nature of panoramic camera views. To address the lack of fisheye camera dataset in autonomous driving tasks, we also build a virtual scene dataset with six fisheye cameras, and the data volume has reached twice that of SemanticKITTI. Experimental results demonstrate that our Sketch-Coloring network significantly enhances 3D perception performance. |
| title | Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2504.01023 |