mirror of
https://github.com/nerfstudio-project/nerfstudio.git
synced 2026-11-10 18:17:31 +08:00
92636c3434
* Add the following fixes to documentation: * Fix trailing backslash in “Use docker image” section * Replace escaped backslash with double-escaped backslash (see Sphinx issue: https://github.com/sphinx-doc/sphinx/issues/6730) * Close backtick in `contributing.md` * Add “run” to instructions for “Render Video” * Remove unnecessary “,” in “Render Video” * Correct “before preceding” to “before proceeding” * Correct “viewpoinrts” to “viewpoints” * Add missing “.” in “Process data” * Specify “bash” for code blocks (for consistency with other blocks in the page) * Fix code block in `viewer_quickstart.rst` (”Copy to clipboard” widget now works) * Fix some code formatting issues in `export_geometry.md` * Correct "harmoincs" to "harmonics" in docs.
63 lines
2.0 KiB
Markdown
63 lines
2.0 KiB
Markdown
# Export geometry
|
|
|
|
Here we document how to export point clouds and meshes from nerfstudio. The main command you'll be working with is `ns-export`. Our point clouds are exported as `.ply` files and the textured meshes are exported as `.obj` files.
|
|
|
|
## Exporting a mesh
|
|
|
|
### 1. TSDF Fusion
|
|
|
|
TSDF (truncated signed distance function) Fusion is a meshing algorithm that uses depth maps to extract a surface as a mesh. This method works for all models.
|
|
|
|
```python
|
|
ns-export tsdf --load-config CONFIG.yml --output-dir OUTPUT_DIR
|
|
```
|
|
|
|
### 2. Poisson surface reconstruction
|
|
|
|
Poisson surface reconstruction gives the highest quality meshes. See the steps below to use Poisson surface reconstruction in our repo.
|
|
|
|
> **Note:**
|
|
> This will only work with a Model that computes or predicts normals, e.g., nerfacto.
|
|
|
|
|
|
1. Train nerfacto with network settings that predict normals.
|
|
|
|
```bash
|
|
ns-train nerfacto --pipeline.model.predict-normals True
|
|
```
|
|
|
|
2. Export a mesh with the Poisson meshing algorithm.
|
|
|
|
```bash
|
|
ns-export poisson --load-config CONFIG.yml --output-dir OUTPUT_DIR
|
|
```
|
|
|
|
## Exporting a point cloud
|
|
|
|
```bash
|
|
ns-export pointcloud --help
|
|
```
|
|
|
|
## Other exporting methods
|
|
|
|
Run the following command to see other export methods that may exist.
|
|
|
|
```python
|
|
ns-export --help
|
|
```
|
|
|
|
## Texturing an existing mesh with NeRF
|
|
|
|
Say you want to simplify and/or smooth a mesh offline, and then you want to texture it with NeRF. You can do that with the following command. It will work for any mesh filetypes that [PyMeshLab](https://pymeshlab.readthedocs.io/en/latest/) can support, for example a `.ply`.
|
|
|
|
```python
|
|
python scripts/texture.py --load-config CONFIG.yml --input-mesh-filename FILENAME --output-dir OUTPUT_DIR
|
|
```
|
|
|
|
## Dependencies
|
|
|
|
Our dependencies are shipped with the pip package in the pyproject.toml file. These are the following:
|
|
|
|
- [xatlas-python](https://github.com/mworchel/xatlas-python) for unwrapping meshes to a UV map
|
|
- [pymeshlab](https://pymeshlab.readthedocs.io/en/latest/) for reducing the number of faces in a mesh
|