Update README.md
Browse files
README.md
CHANGED
|
@@ -2,13 +2,13 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
-
|
| 6 |
|
| 7 |
Download [FlowOcc3D](https://huggingface.co/viewformer/ViewFormer-Occ/blob/main/occ_flow_sparse_ext.zip). Unzip it in `./data/nuscenes`.
|
| 8 |
|
| 9 |
Our FlowOcc3D assigns a flow vector to each foreground occupancy of [Occ3D](https://github.com/CVPR2023-3D-Occupancy-Prediction/CVPR2023-3D-Occupancy-Prediction).
|
| 10 |
|
| 11 |
-
Here we briefly introduce
|
| 12 |
```python
|
| 13 |
W, H, Z = 200, 200, 16
|
| 14 |
sample_idx = results['sample_idx'] # nuScenes sample token
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
+
# FlowOcc3D (3D Occypancy Flow Dataset)
|
| 6 |
|
| 7 |
Download [FlowOcc3D](https://huggingface.co/viewformer/ViewFormer-Occ/blob/main/occ_flow_sparse_ext.zip). Unzip it in `./data/nuscenes`.
|
| 8 |
|
| 9 |
Our FlowOcc3D assigns a flow vector to each foreground occupancy of [Occ3D](https://github.com/CVPR2023-3D-Occupancy-Prediction/CVPR2023-3D-Occupancy-Prediction).
|
| 10 |
|
| 11 |
+
Here we briefly introduce how to use FlowOcc3D. We store the flow and index of each foreground voxel in the `xxx.bin` file and `xxx_idx.bin` file.
|
| 12 |
```python
|
| 13 |
W, H, Z = 200, 200, 16
|
| 14 |
sample_idx = results['sample_idx'] # nuScenes sample token
|