New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Implementing CAT with GNN #13

Open

yogeshhk opened this issue Jun 11, 2023 · 0 comments

Labels

RnD

Owner

yogeshhk commented Jun 11, 2023 •

edited

Loading

Chordal Axis Transform like approach along with Link Prediction of Graph Neural Network can be combined to generate midcurves.

Training data: Supervised

Profile and its midcurve data is available
Triangulate profile shape. Get midpoints of all sides of all triangles. Make a graph.
In the graph, for 2D profile, only certain links are active (basically the outer shape, for midcurve some other links are active, basically the middle ones.
Now the problem boils down to, given both inputs and output topologies, can we predict midcurve links given profile graph and links.

yogeshhk added the RnD label

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment