search

autonomousvision / convolutional_occupancy_networks

[ECCV'20] Convolutional Occupancy Networks
https://pengsongyou.github.io/conv_onet
MIT License
830 stars 113 forks source link

Inference/Generate with a generic .ply file #42

Closed DuncanZauss closed 2 years ago

DuncanZauss commented 2 years ago

Hi, Thank you for making the code for this nice project publicly available. If I have a point cloud stored in a generic .ply file, how can I process it in such a way that I can run inference with the model that was trained on matterport? So is there some "build_dataset.py" file that is not for a specific dataset, but can just be used for a normal .ply file? Best, Duncan

pengsongyou commented 2 years ago

You can have a look at the demo data for the matterport3D scene, and need to transfer your .ply file to the corresponding .npz file first. Then you simply need to modify this line of the config file.

Hope it helps.

DuncanZauss commented 2 years ago

Thank you for the reply. Just a quick follow up question: What is the normals.npy file within npz file used for? From what I understood from your paper, only the location of the points matters, but not their (surface) normal.

pengsongyou commented 2 years ago

@DuncanZauss We don't use the normals as inputs, but use it for evaluation only.