paul007pl / VRCNet

[CVPR 2021 Oral] Variational Relational Point Completion Network
https://paul007pl.github.io/projects/VRCNet.html
MIT License
156 stars 29 forks source link

About the Loss #32

Open lyb92nlf opened 1 year ago

lyb92nlf commented 1 year ago

Thanks for your great work! @paul007pl

In your implementation, the four variables generated by this code do not seem to be the same as the description in the paper. Can you elaborate on the meanings and functions of these four variables? Thank you! coarse_raw, coarse_high, coarse, fine = self.decoder(feat, x)

Looking forward to your reply!