kaolin
kaolin copied to clipboard
A PyTorch Library for Accelerating 3D Deep Learning Research
I want to use nn.DataParallel for multiple-gpu training of sparse convolution in structed point cloud. However, the spc class contain spc.octrees, which is of data type uint8. So It will...
The method of kaolin.ops.spc.Conv3d is great to handle batches of spc features. However, when I want to write a self-attention layer, I need to use nn.linear. That means, have to...
Hello, I try to render glb file following this [tutorial](https://github.com/NVIDIAGameWorks/kaolin/blob/master/examples/tutorial/gltf_viz.ipynb). However, I found that the shadow on the ground cannot be rendered. For example, the first pic is rendered by...
Hello, I have a model with pbr mat which has transparent part ,but I don't know how to render it correctly. I got the basecolor of the transparent part instead...
Hi there, and thanks so much for keeping this project alive with new features. I am currently using structured point clouds, and I would like to know if there is...
Fixes `projection_matrix` function in `intrinsics_ortho.py`: - Use the `top, bottom, right, left` formula for orthogonal projections ``` top = 1.0 bottom = -top right = 1.0 * self.width / self.height...
I don't particularly understand why the projection matrix function `projection_matrix` of the orthographic camera uses the following calculation formulas for `top, bottom, right, left`. The ndc coordinates calculated in this...
Hello, I am a senior Game Developer. I want to contribute to this open source.
I have discovered that under certain NVIDIA driver versions and OpenGL versions, using nvdiffrast within kaolin to render causes errors. As mentioned in this issue https://github.com/sicxu/Deep3DFaceRecon_pytorch/issues/2, the problem is related...