Caenorst
Caenorst
Hi @FavorMylikes , thank you for your interest in Kaolin, here is the dataset we used https://graphics.pixar.com/usd/release/dl_kitchen_set.html
We do not offer obj exporter, what software are you using? The tutorial generate an USD checkpoint for you, you can do the comparison in Omniverse
Hi @FavorMylikes , you can find how we are using the metadata in our loader: https://github.com/NVIDIAGameWorks/kaolin/blob/master/kaolin/io/render.py#L106-L125
Hi @Entongsu , can you elaborate on the data structure / kind of rendering?
Hi @Dipankar1997161 , what is your gcc version?
Can I have more details about your OS, GPU, pytorch version, python version, and kaolin version? (I see a 0.1 in your folder name)
Hi @qiminchen , thank you for your interest in Kaolin. Great timing! I just pushed an MR for data preprocessing, including [a small example doing exactly what you are asking...
It should also work with V1 (just change the dataset name), I would be careful with ShapeNetV1 as I found out that a big part of the dataset is just...
Glad to hear that it's working well for you! Wxtracting normals should be pretty easy to extend, you should be able to get the normal using https://kaolin.readthedocs.io/en/latest/modules/kaolin.ops.mesh.html#kaolin.ops.mesh.face_normals (I need to...
The problem is from ShapeNet, some models have very weird internal structures that are overlapping with the visible shape. I've observed that when using the rasterization: typically you will have...