luost26 / diffusion-point-cloud

:thought_balloon: Diffusion Probabilistic Models for 3D Point Cloud Generation (CVPR 2021)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Which place do you use the autoencoder ?

OswaldoBornemann opened this issue · comments

I noticed that in your code, you train an autoencoder, but in the generation code, it seems that you don't use it. So you train an autoencoder and generator but in the final you just use the generator ?

Auto-encoding and generation were treated as two different tasks then.

Oh i see. Thank you very much.

Oh i see. Thank you very much.

hi, i don't konw the difference of tow files. Could you tell me the details?