sparse-mvs-2

Asking support for pytorch 2.0.1.

3

I'm using kaolin on other project which requires pytorch 2.0.1, which will get: No module named 'torch._six'.

Bug report on importing mesh.

7

I'm trying to bring in a mesh into kaolin, but I've discovered an issue with the kaolin.io.obj.import_mesh function. Specifically, import_mesh doesn't currently support OBJ files that include color information. If...

Issus on Rasterize

1

I am using rasterize function. However, the rendered image looks like this:  Seems that the mesh in the back render first.

SNode support on macOS

2

I'm currently trying to deploy taichi on macOS. Is there any chance that this issue can solve? Since Pointer SNode is not supported on macOS. ############################################### sorry about that but...

Asking support for multiple-gpu training of structed point cloud class

2

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...

Asking support for linear layer in spc features.

1

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...

[New!] The 3D version of VAR is coming🔥. With 512-Byte code can represent and generate delicated geometry, with 2000× compression 🔥 and better F-score 🔥.

1

Project page: [https://sparse-mvs-2.github.io/VAT.IO/](https://sparse-mvs-2.github.io/VAT.IO/) Different from VAR, we introduce **Variational Tokenizer (VAT)**, combine the discrete tokenizer with a variational autoencoder (VAE), which has been proven to be necessary for 3D features....