getting latent code from point clouds

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

1.48k stars 291 forks source link

getting latent code from point clouds #88

Open kohlisimranjit opened 3 years ago

kohlisimranjit commented 3 years ago

Hi, thank you for the good work! I would like to use your pretrained model to get latent codes using point clouds or .off files. I am not able to figure out how to do it. The paper and .yaml files mention that the point cloud is sample at 2048. But seems like in generation.py c = self.model.encode_inputs(inputs) always has inputs of shape 1,300,3