search

PeterouZh / CIPS-3D

3D-aware GANs based on NeRF (arXiv).
MIT License
610 stars 60 forks source link

How to test other datasets #7

Closed Stephanie-ustc closed 2 years ago

Stephanie-ustc commented 2 years ago

Hi，how to test other datasets? change the datasets/pretrained/metadata.json?

PeterouZh commented 2 years ago

At present, I only provide models for two datasets. More models will be provided later.

I do not quite understand what you mean.

Do you want to train on other datasets?

Stephanie-ustc commented 2 years ago

I want test some other image on your model. But I dont konw how to do it. If I have image sequence with pose data，how to test？

PeterouZh commented 2 years ago

I want test some other image on your model. But I dont konw how to do it. If I have image sequence with pose data，how to test？

  1. Align the images in the way of StyleGAN. You can refer to this script align_images.py.
  2. Project the aligned images into the W space, also known as GAN inversion. Different from the common 2D inversion, you'd better set an appropriate yaw/pitch/fov for the CIPS-3D generator to make the initial pose of G(w) and the image to be inverted consistent.
  3. After you get the w of the image, you can reconstruct images of different styles using G'(w). G' can be obtained by interpolating generators of different domains.

Hope this helps.