search

lychenyoko / content-aware-gan-compression

CVPR2021 Content-Aware GAN Compression
MIT License
64 stars 7 forks source link

Question about the generation for style-mixed images and morphed images as shown in Figure 5 in the main paper #7

Closed kminsoo closed 2 years ago

kminsoo commented 3 years ago

Hi!

I would like to ask you about which codes I run for generating the style-mixed and morphed images.

Thanks!

lychenyoko commented 3 years ago

Hi,

I am following [1,2] for style-mixing and image morphing. You may reuse some codes from Image_Projector under Evaluation/image_projection/image_projector.py to implement the two editing.

[1] Abdal, Rameen, Yipeng Qin, and Peter Wonka. "Image2stylegan: How to embed images into the stylegan latent space?." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019. [2] Abdal, Rameen, Yipeng Qin, and Peter Wonka. "Image2stylegan++: How to edit the embedded images?." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020.

kminsoo commented 2 years ago

Thank you so much!