correspondence using non-functional maps methods

nmwsharp / diffusion-net

Pytorch implementation of DiffusionNet for fast and robust learning on 3D surfaces like meshes or point clouds.

https://arxiv.org/abs/2012.00888

MIT License

408 stars 51 forks source link

correspondence using non-functional maps methods #24

Open mfarazi1991 opened 2 years ago

mfarazi1991 commented 2 years ago

Hi,

First thanks for sharing your amazing work! I have a shape correspondence model that does not use functional maps but rather a descriptor based created by a graph neural network. I am not sure how to calculate the correspondence on the test set with .vts files that have a different number of vertices. Mine works fine on the test set with the same number of vertices, not variable ones. Any code that you can share with me for this? Thanks!