OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916363602231296 |
|---|---|
| author | Zhang, Chubin Yan, Juncheng Wei, Yi Li, Jiaxin Liu, Li Tang, Yansong Duan, Yueqi Lu, Jiwen |
| author_facet | Zhang, Chubin Yan, Juncheng Wei, Yi Li, Jiaxin Liu, Li Tang, Yansong Duan, Yueqi Lu, Jiwen |
| contents | Occupancy prediction reconstructs 3D structures of surrounding environments. It provides detailed information for autonomous driving planning and navigation. However, most existing methods heavily rely on the LiDAR point clouds to generate occupancy ground truth, which is not available in the vision-based system. In this paper, we propose an OccNeRF method for training occupancy networks without 3D supervision. Different from previous works which consider a bounded scene, we parameterize the reconstructed occupancy fields and reorganize the sampling strategy to align with the cameras' infinite perceptive range. The neural rendering is adopted to convert occupancy fields to multi-camera depth maps, supervised by multi-frame photometric consistency. Moreover, for semantic occupancy prediction, we design several strategies to polish the prompts and filter the outputs of a pretrained open-vocabulary 2D segmentation model. Extensive experiments for both self-supervised depth estimation and 3D occupancy prediction tasks on nuScenes and SemanticKITTI datasets demonstrate the effectiveness of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_09243 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments Zhang, Chubin Yan, Juncheng Wei, Yi Li, Jiaxin Liu, Li Tang, Yansong Duan, Yueqi Lu, Jiwen Computer Vision and Pattern Recognition Occupancy prediction reconstructs 3D structures of surrounding environments. It provides detailed information for autonomous driving planning and navigation. However, most existing methods heavily rely on the LiDAR point clouds to generate occupancy ground truth, which is not available in the vision-based system. In this paper, we propose an OccNeRF method for training occupancy networks without 3D supervision. Different from previous works which consider a bounded scene, we parameterize the reconstructed occupancy fields and reorganize the sampling strategy to align with the cameras' infinite perceptive range. The neural rendering is adopted to convert occupancy fields to multi-camera depth maps, supervised by multi-frame photometric consistency. Moreover, for semantic occupancy prediction, we design several strategies to polish the prompts and filter the outputs of a pretrained open-vocabulary 2D segmentation model. Extensive experiments for both self-supervised depth estimation and 3D occupancy prediction tasks on nuScenes and SemanticKITTI datasets demonstrate the effectiveness of our method. |
| title | OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.09243 |