turn on camera opt by default (#727)

* camera opt by default

* fix tests
This commit is contained in:
Ethan Weber authored and GitHub committed 2022-10-07 11:21:21 -07:00
1 parent 9afe03eb4c
commit ee94f23f83
4 files changed
+33 -21

No files matched your search

+6 -7
View File
@@ -110,16 +110,17 @@ cd vcpkg
## Record3D Capture
Nerfstudio can also be trained directly from >=iPhone 12 Pro captures from the [Record3D app](https://record3d.app/). This uses the iPhone's LiDAR sensors to calculate camera poses, so COLMAP is not needed.
Nerfstudio can also be trained directly from >=iPhone 12 Pro captures from the [Record3D app](https://record3d.app/). This uses the iPhone's LiDAR sensors to calculate camera poses, so COLMAP is not needed.
Record a video and export with the EXR + JPG sequence format.
Record a video and export with the EXR + JPG sequence format.
<img src="imgs/record_3d_video_selection.png" width=150>
<img src="imgs/record_3d_export_selection.png" width=150>
Then, move the exported capture folder from your iPhone to your computer.
```
ns-train nerfacto --pipeline.datamanager.camera-optimizer.mode SO3xR3 record3d-data --data {RECORD3D_CAPTURE_DIR/EXR_RGBD}
ns-train nerfacto record3d-data --data {RECORD3D_CAPTURE_DIR/EXR_RGBD}
```
You can try with our data to see the correct formatting.
@@ -130,8 +131,6 @@ ns-download-data --dataset record3d
This will download data to `data/record3d/bear`. Then you can train, and don't forget to open up the viewer.
```python
ns-train nerfacto --pipeline.datamanager.camera-optimizer.mode SO3xR3 record3d-data --data data/record3d/bear
```shell
ns-train nerfacto record3d-data --data data/record3d/bear
```
Notice we are adding the option `--pipeline.datamanager.camera-optimizer.mode SO3xR3`, which is experimental but turns on camera pose optimization for higher quality results with record3d. This is because the camera poses from record3d are quite noisy, unlike those from COLMAP (from the `ns-process-data` script).