kaolin icon indicating copy to clipboard operation
kaolin copied to clipboard

A PyTorch Library for Accelerating 3D Deep Learning Research

Results 237 kaolin issues
Sort by recently updated
recently updated
newest added

### Description Get the Pixel2Mesh example working ### Tasks - [x] Get main train.py and eval.py scripts working, change arguments - [x] Fix an error if all the faces of...

Load meshes with heterogeneous polys by converting all faces to triangles. - Created a new asset for testing (rocket.obj) which includes heterogeneous polys - Updated Mesh class to automatically convert...

Corrected `face_textures` in places where `vt` was optional for face

Hey, im trying to use this great framework to do texture optimization but im facing the next isssue, all the steps to reproduce are in this colab notebook. https://colab.research.google.com/drive/1K6oT4DD7NroacY3jd6k-62QI7PzLGnXM?usp=sharing key...

Description: This pull request corrects minor typographical errors in the codebase: - In `kaolin/ops/spc/bf_recon.py`, the word "cummulative" was corrected to "cumulative" in a comment. - In `kaolin/render/camera/intrinsics_pinhole.py`, the word "heigh"...

I have torch version 2.6.0+rocm6.2.4 on Linux and cant install kaolin. > git clone https://github.com/NVIDIAGameWorks/kaolin.git > cd kaolin > pip install . > ... > ImportError: Kaolin requires PyTorch >=...

no-issue-activity

Current behavior: `kaolin.visualize.IpyTurntableVisualizer` and `kaolin.visualize.FirstPersonVisualizer` take an input camera and modify it in a difficult to predict way according to input arguments: ``` visualizer = kaolin.visualize.IpyTurntableVisualizer( cam.height, cam.width, copy.deepcopy(cam), render,...

no-issue-activity

I get the following error when using the render function below to render a scene and then deform a set of points and faces to match the scene: # ERROR...

no-issue-activity

Hi I am trying to install and meet this: [x@machine ~]$ pip install kaolin==0.17.0 -f https://nvidia-kaolin.s3.us-east-2.amazonaws.com/torch-2.7.0_cu128.html Looking in links: https://nvidia-kaolin.s3.us-east-2.amazonaws.com/torch-2.7.0_cu128.html ERROR: Could not find a version that satisfies the requirement...

The installation instructions here recommend installing prebuilt wheels, but this cuts off at torch 2.5.1 and cuda 12.6 https://kaolin.readthedocs.io/en/latest/notes/installation.html Can new torch/cuda versions be supported there? Does this repo maintain...