Views
No views yet
1.
2├── stage-1/
3│ ├── low_resolution.pth
4│ └── high_resolution.pth
5└── stage-2/
6 ├── nuscenes.pth
7 └── multi-datasets.pth| Checkpoint type | File | Intended use |
|---|---|---|
| GeoUP Pretrain Ckpts | stage-1/low_resolution.pth | Initialize GeoUP for low-resolution input recipes, including the nuScenes multi-task configuration. |
| GeoUP Pretrain Ckpts | stage-1/high_resolution.pth | Initialize GeoUP for high-resolution input recipes, including the joint multi-dataset configuration. |
| GeoUP Ckpts | stage-2/nuscenes.pth | Final nuScenes model for 3D detection, semantic occupancy prediction, metric depth estimation, and camera-pose evaluation. |
| GeoUP Ckpts | stage-2/multi-datasets.pth | Final jointly trained model for nuScenes, Argoverse 2, Waymo, KITTI, and DDAD. |
1@article{xu2026geometry,
2 title={Geometry-Grounded Unified 3D Perception for Autonomous Driving},
3 author={Xu, Longfei and Wang, Xiaohui and Huang, Zehao and Li, Han and Yang, Ya and Wang, Naiyan and Liu, Si},
4 journal={arXiv preprint arXiv:2608.13147},
5 year={2026}
6}