DualBEV: Unifying Dual View Transformation with Probabilistic Correspondences
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929499385364480 |
|---|---|
| author | Li, Peidong Shen, Wancheng Huang, Qihao Cui, Dixiao |
| author_facet | Li, Peidong Shen, Wancheng Huang, Qihao Cui, Dixiao |
| contents | Camera-based Bird's-Eye-View (BEV) perception often struggles between adopting 3D-to-2D or 2D-to-3D view transformation (VT). The 3D-to-2D VT typically employs resource-intensive Transformer to establish robust correspondences between 3D and 2D features, while the 2D-to-3D VT utilizes the Lift-Splat-Shoot (LSS) pipeline for real-time application, potentially missing distant information. To address these limitations, we propose DualBEV, a unified framework that utilizes a shared feature transformation incorporating three probabilistic measurements for both strategies. By considering dual-view correspondences in one stage, DualBEV effectively bridges the gap between these strategies, harnessing their individual strengths. Our method achieves state-of-the-art performance without Transformer, delivering comparable efficiency to the LSS approach, with 55.2% mAP and 63.4% NDS on the nuScenes test set. Code is available at \url{https://github.com/PeidongLi/DualBEV} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05402 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DualBEV: Unifying Dual View Transformation with Probabilistic Correspondences Li, Peidong Shen, Wancheng Huang, Qihao Cui, Dixiao Computer Vision and Pattern Recognition Camera-based Bird's-Eye-View (BEV) perception often struggles between adopting 3D-to-2D or 2D-to-3D view transformation (VT). The 3D-to-2D VT typically employs resource-intensive Transformer to establish robust correspondences between 3D and 2D features, while the 2D-to-3D VT utilizes the Lift-Splat-Shoot (LSS) pipeline for real-time application, potentially missing distant information. To address these limitations, we propose DualBEV, a unified framework that utilizes a shared feature transformation incorporating three probabilistic measurements for both strategies. By considering dual-view correspondences in one stage, DualBEV effectively bridges the gap between these strategies, harnessing their individual strengths. Our method achieves state-of-the-art performance without Transformer, delivering comparable efficiency to the LSS approach, with 55.2% mAP and 63.4% NDS on the nuScenes test set. Code is available at \url{https://github.com/PeidongLi/DualBEV} |
| title | DualBEV: Unifying Dual View Transformation with Probabilistic Correspondences |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.05402 |