FastViDAR: Real-Time Omnidirectional Depth Estimation via Alternative Hierarchical Attention
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912612617289728 |
|---|---|
| author | Zhao, Hangtian Chen, Xiang Li, Yizhe Wang, Qianhao Lu, Haibo Gao, Fei |
| author_facet | Zhao, Hangtian Chen, Xiang Li, Yizhe Wang, Qianhao Lu, Haibo Gao, Fei |
| contents | In this paper we propose FastViDAR, a novel framework that takes four fisheye camera inputs and produces a full $360^\circ$ depth map along with per-camera depth, fusion depth, and confidence estimates. Our main contributions are: (1) We introduce Alternative Hierarchical Attention (AHA) mechanism that efficiently fuses features across views through separate intra-frame and inter-frame windowed self-attention, achieving cross-view feature mixing with reduced overhead. (2) We propose a novel ERP fusion approach that projects multi-view depth estimates to a shared equirectangular coordinate system to obtain the final fusion depth. (3) We generate ERP image-depth pairs using HM3D and 2D3D-S datasets for comprehensive evaluation, demonstrating competitive zero-shot performance on real datasets while achieving up to 20 FPS on NVIDIA Orin NX embedded hardware. Project page: \href{https://3f7dfc.github.io/FastVidar/}{https://3f7dfc.github.io/FastVidar/} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23733 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FastViDAR: Real-Time Omnidirectional Depth Estimation via Alternative Hierarchical Attention Zhao, Hangtian Chen, Xiang Li, Yizhe Wang, Qianhao Lu, Haibo Gao, Fei Computer Vision and Pattern Recognition Robotics In this paper we propose FastViDAR, a novel framework that takes four fisheye camera inputs and produces a full $360^\circ$ depth map along with per-camera depth, fusion depth, and confidence estimates. Our main contributions are: (1) We introduce Alternative Hierarchical Attention (AHA) mechanism that efficiently fuses features across views through separate intra-frame and inter-frame windowed self-attention, achieving cross-view feature mixing with reduced overhead. (2) We propose a novel ERP fusion approach that projects multi-view depth estimates to a shared equirectangular coordinate system to obtain the final fusion depth. (3) We generate ERP image-depth pairs using HM3D and 2D3D-S datasets for comprehensive evaluation, demonstrating competitive zero-shot performance on real datasets while achieving up to 20 FPS on NVIDIA Orin NX embedded hardware. Project page: \href{https://3f7dfc.github.io/FastVidar/}{https://3f7dfc.github.io/FastVidar/} |
| title | FastViDAR: Real-Time Omnidirectional Depth Estimation via Alternative Hierarchical Attention |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2509.23733 |