AdaOcc: Adaptive Forward View Transformation and Flow Modeling for 3D Occupancy and Flow Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911939283648512 |
|---|---|
| author | Chen, Dubing Han, Wencheng Fang, Jin Shen, Jianbing |
| author_facet | Chen, Dubing Han, Wencheng Fang, Jin Shen, Jianbing |
| contents | In this technical report, we present our solution for the Vision-Centric 3D Occupancy and Flow Prediction track in the nuScenes Open-Occ Dataset Challenge at CVPR 2024. Our innovative approach involves a dual-stage framework that enhances 3D occupancy and flow predictions by incorporating adaptive forward view transformation and flow modeling. Initially, we independently train the occupancy model, followed by flow prediction using sequential frame integration. Our method combines regression with classification to address scale variations in different scenes, and leverages predicted flow to warp current voxel features to future frames, guided by future frame ground truth. Experimental results on the nuScenes dataset demonstrate significant improvements in accuracy and robustness, showcasing the effectiveness of our approach in real-world scenarios. Our single model based on Swin-Base ranks second on the public leaderboard, validating the potential of our method in advancing autonomous car perception systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01436 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AdaOcc: Adaptive Forward View Transformation and Flow Modeling for 3D Occupancy and Flow Prediction Chen, Dubing Han, Wencheng Fang, Jin Shen, Jianbing Computer Vision and Pattern Recognition Robotics In this technical report, we present our solution for the Vision-Centric 3D Occupancy and Flow Prediction track in the nuScenes Open-Occ Dataset Challenge at CVPR 2024. Our innovative approach involves a dual-stage framework that enhances 3D occupancy and flow predictions by incorporating adaptive forward view transformation and flow modeling. Initially, we independently train the occupancy model, followed by flow prediction using sequential frame integration. Our method combines regression with classification to address scale variations in different scenes, and leverages predicted flow to warp current voxel features to future frames, guided by future frame ground truth. Experimental results on the nuScenes dataset demonstrate significant improvements in accuracy and robustness, showcasing the effectiveness of our approach in real-world scenarios. Our single model based on Swin-Base ranks second on the public leaderboard, validating the potential of our method in advancing autonomous car perception systems. |
| title | AdaOcc: Adaptive Forward View Transformation and Flow Modeling for 3D Occupancy and Flow Prediction |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2407.01436 |