PyTorch3D: Difference between revisions
No edit summary |
|||
| (One intermediate revision by the same user not shown) | |||
| Line 3: | Line 3: | ||
This Facebook AI Research's PyTorch 3D graphics library. | This Facebook AI Research's PyTorch 3D graphics library. | ||
The main features are | The main features are differentiable mesh and point cloud renderers written in CUDA. | ||
==Install== | ==Install== | ||
Latest revision as of 19:33, 22 September 2020
PyTorch3D
This Facebook AI Research's PyTorch 3D graphics library.
The main features are differentiable mesh and point cloud renderers written in CUDA.
Install
See INSTALL.md. I've only been able to get it to work on Linux.
- Make sure you have CUDA, CUDNN, PyTorch installed
pip install 'git+https://github.com/facebookresearch/pytorch3d.git'
- Notes
- The pip version does not include CUDA support. Install it from the git repo.
- You need to recompile and reinstall PyTorch3D every time you upgrade PyTorch.
Usage
Point Cloud Renderer
See render_colored_points.ipynb. You can run this tutorial in Colab using this link or the Open in Colab' extension.
To implement custom cameras (e.g. Fisheye, 360), you can write your own custom PointsRasterizer. See /pytorch3d/renderer/points/rasterizer.py for the default PointsRasterizer.
Specifically, you can change the transform function to a custom function which calculates screen coordinates from world coordinates.