OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction
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_ | 1866914863896330240 |
|---|---|
| author | Zhang, Ji Ding, Yiran Liu, Zixin |
| author_facet | Zhang, Ji Ding, Yiran Liu, Zixin |
| contents | 3D occupancy prediction based on multi-sensor fusion,crucial for a reliable autonomous driving system, enables fine-grained understanding of 3D scenes. Previous fusion-based 3D occupancy predictions relied on depth estimation for processing 2D image features. However, depth estimation is an ill-posed problem, hindering the accuracy and robustness of these methods. Furthermore, fine-grained occupancy prediction demands extensive computational resources. To address these issues, we propose OccFusion, a depth estimation free multi-modal fusion framework. Additionally, we introduce a generalizable active training method and an active decoder that can be applied to any occupancy prediction model, with the potential to enhance their performance. Experiments conducted on nuScenes-Occupancy and nuScenes-Occ3D demonstrate our framework's superior performance. Detailed ablation studies highlight the effectiveness of each proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05329 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction Zhang, Ji Ding, Yiran Liu, Zixin Computer Vision and Pattern Recognition 3D occupancy prediction based on multi-sensor fusion,crucial for a reliable autonomous driving system, enables fine-grained understanding of 3D scenes. Previous fusion-based 3D occupancy predictions relied on depth estimation for processing 2D image features. However, depth estimation is an ill-posed problem, hindering the accuracy and robustness of these methods. Furthermore, fine-grained occupancy prediction demands extensive computational resources. To address these issues, we propose OccFusion, a depth estimation free multi-modal fusion framework. Additionally, we introduce a generalizable active training method and an active decoder that can be applied to any occupancy prediction model, with the potential to enhance their performance. Experiments conducted on nuScenes-Occupancy and nuScenes-Occ3D demonstrate our framework's superior performance. Detailed ablation studies highlight the effectiveness of each proposed method. |
| title | OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.05329 |