Dear Grasshopper community,
We are making a brace for medical purposes. For this brace, we 3D scan the patient. From this scan, we select landmarks. These landmarks are used for orienting the scan, and then used as reference points for building the brace itself. Now, we select these points by hand.
However, we’ve come across a deep learning algorithm by RasmusRPaulsen that generates landmarks on the face automatically. Here is his code: GitHub - RasmusRPaulsen/Deep-MVLM: A tool for precisely placing 3D landmarks on 3D facial scans based on the paper "Multi-view Consensus CNN for 3D Facial Landmark Placement"
I’ve tried implementing this code into the Grasshopper Python component. However, I ran into some problems. Largely due to my very limited knowledge in python 
. The first problem I’m experiencing is importing modules. I’ve read that the plugin GH PYTHON REMOTE could help, but this limits me to the normal python modules, and not the modules used in the code by RasmusRPaulsen. But even after importing the modules, I expect to exerpience way more problems.
Eventually, the idea would also be to train the deep learning algorithm to also pick certain landmarks on the neck, but this is very ambitious. We would be very happy with getting the landmarks of the face outputted from the Grasshopper script.
Thanks for your help in advance!
I’ve included the grasshopper script here:
V13 automation of landmarks.gh (4.4 MB)