Jonny Jackson

@itszash @SmitSheth I'm not affiliated with this work, but I've found that there's a script called **occupancy_networks/scripts/sample_mesh.py**. It turns an [OFF mesh file](https://en.wikipedia.org/wiki/OFF_(file_format)) into the points.npz and model.binvox files needed....

@itszash This is a supervised machine learning model, so with every example (e.g. a set of images of the same object, as in your case) the algorithm needs to see...

To extend my earlier answer somewhat: > If you don't have this 3D representation of the "correct answer" (you'll generally see it referred to as 'ground truth') then you'll need...

@noamgat I'm not affiliated with this work but see my fixes [here](https://github.com/autonomousvision/occupancy_networks/compare/master...jnyjxn:master).

@LMescheder If it helps, I've made all the necessary fixes in [this fork](https://github.com/autonomousvision/occupancy_networks/compare/master...jnyjxn:master). Specifically, *im2mesh/utils/binvox_rw.py* and *scripts/sample_mesh.py* need to be changed.

Thanks @HobbitLong - unfortunately from what I can tell ImageNet is defunct (I've had no response for > 3 months) so I can't access the dataset. Could you briefly describe...

@HobbitLong thanks for this additional info. Just to confirm, the use of a patch-wise method here is only motivated by a small dataset? I am also trying to find an...

You need to use an environment running Python 3.6. e.g. `conda create -n pptk_env python=3.6`

Hello, I'm using this space to share my Dockerfile solution to install Kaolin with CUDA support on an Nvidia RTX 3090 (should be the same on 3080/3070 as well). _It's...

Hello, it's possible that [this comment](https://github.com/NVIDIAGameWorks/kaolin/issues/449#issuecomment-1001022900) I made on another issue might help, if you are using Docker.