graphics
graphics copied to clipboard
Non rigid deformation between a template and target mesh with different vertices
This is an amazing library, I was wonder if is possible to model As Conformal As Possible fitting energy between two meshes that have completely different vertex and edge information with this library?
Example:
mesh_1 contains 10000 vertices and 25000 faces mesh_2 contains 2000 vertices and 10000 faces, in this case, how would we proceed ?
The Chamfer loss function doesn't require the two meshes to have the same number of vertices, so you could use that as a start.
In general, Tensorflow doesn't care if the predictions and the ground truth don't have the same shape, but most losses expect it.