search

SimingYan / IAE

[ICCV 2023] "Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning"
99 stars 17 forks source link

How to pretrain using PointNext backbone as encoder? #14

Closed Daniellli closed 1 year ago

Daniellli commented 1 year ago

hi, I am curious of how to pertrain with other backbone such as PointNext. And, as shown in your paper, you experiment with PointNext and show a promising results. Could you release the PointNext pretrain code.

appreciate for your help.

SimingYan commented 1 year ago

We will public the new backbone model later. If you have read and understand our paper, you should find it is very easy to replace the encoder backbone. I would appreciate it a lot if you can also try to implement by yourself.