search

autonomousvision / occupancy_networks

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"
https://avg.is.tuebingen.mpg.de/publications/occupancy-networks
MIT License
1.49k stars 291 forks source link

Normalization of shapes #77

Open Hippogriff opened 4 years ago

Hippogriff commented 4 years ago

I am trying to test different kind of sampling of points around the shape, using a different code base. But I am using your MSE to generate mesh based on predicted SDF. I would like to know the exact normalization that you do on every mesh. For example, can I get a small script that takes vertices of mesh (N x 3) as input and returns the normalized version of vertices? The normalization I presume includes shifting, scaling and padding.

albertotono commented 3 years ago

@Hippogriff did yo try the sampling operation from Pytorch3D? maybe that can help you. they have detailed explanations about how their works