search

eladrich / pixel2style2pixel

Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework
https://eladrich.github.io/pixel2style2pixel/
MIT License
3.19k stars 570 forks source link

Request for pre-trained models of competitors in Figure 8 and Figure 9 #298

Closed Yikai-Wang closed 1 year ago

Yikai-Wang commented 1 year ago

Hi there, Thanks for your great work! I am very interested in your method and want to do some follow up work. Some competitors in your paper do not provide the corresponding pre-trained models, for example pix2pixHD in sketch2image task, and pix2pixHD, SPADE, CC FPSE for label2image task. I wonder if you could share those checkpoints so we can run some generation results and compare. Look forward to your reply!

yuval-alaluf commented 1 year ago

I don't believe we still have those models available, but all data details are provided in the paper. We used the default parameters for all competitors so re-creating the models should be fairly straightforward.

Yikai-Wang commented 1 year ago

Thanks for your reply.