Max Benjamin Eschenbach

Alright, thank you for clarifying! I don't wanted to bother but raise awareness since I noticed while trying to update my research environments this morning :) Best wishes, Max

here is an attempt to solve this: https://github.com/fstwn/compute.rhino3d/blob/f4a9c8f49bfffe0bdbf9ec5c72f6083b49b0d1d0/src/ghhops-server-py/ghhops_server/params.py#L194 let me know if there is a way to contribute more directly (i'll also tag @eirannejad since he seems to be quite...

Hi again and thank you for your reply! You are right, I just tested it by initializing a new conda env and running the `human_segmentation_original` experiment by calling `python human_segmentation_original.py...

Hey @nmwsharp @pvnieo I just did some tries again. Here is an `environment.yml` that mostly did the trick for me: [https://github.com/fstwn/diffusion-net/blob/3cdeb8a7a0b98c12c6bb8c48c2a650a49090792e/environment.yml](https://github.com/fstwn/diffusion-net/blob/3cdeb8a7a0b98c12c6bb8c48c2a650a49090792e/environment.yml) I ran all your experiments with the following results:...

Always glad to help and contribute 🙏

I would recommend using igl for this step: https://github.com/libigl/libigl-python-bindings/ you can then call: `isoV, isoE = igl.isolines(V, F, z, n)` where V #V by dim list of mesh vertex positions...

Now scammers are trying to whitelist their accounts? lol?! Or ist this a legit project/account?

This has to be addressed! It will probably be necessary to restructure all the graphs to directional graphs and employ consistent directions from the get go. Lot's of work bu...

This is related to the routine for using the least angle change connection. We need a failsafe here to prevent "parallel" edges from accross the tube being used.

Maybe implement some reference geometry query to deal with this