mganprior
mganprior copied to clipboard
genforce
[CVPR 2020] Image Processing Using Multi-Code GAN Prior
Hello. For the image super-resolution task, in your code, you just save the low-resolution image and the inversion results without using Eq.(7) for optimization. Could you please tell me how...
Hello, first of all thanks for your excelent work. I tried to reproduce your lsun bedroom inversion and results are not that bad. Although they are not the same as...
Thanks for your great work in GAN inversion. I find a bug when I set the generator_type as stylegan. I guess that line 69 in `derivable_generator.py` should be `self.stylegan =...
For image super-resolution task，are all the parameters to be optimized just N latent vectors and N adaptive channel importance weights?Do parameters such as convolution weights in the pre-trained PGGAN model...
I run : python inpainting.py --gan_model pggan_bedroom --target_images ./examples/inpainting/bedroom --outputs ./inpainting --mask ./examples/masks/mask-1.png --video False --composing_layer 8 --z_number 20 --optimization Adam --iterations 6000 although even with --video False it creates...
Here's a link https://paperswithcode.com/paper/image2stylegan-how-to-embed-images-into-the. Thanks.
I haven't download the released code to have a try. Could you tell me how long should I take to get the multiple latent codes of a image (the optimization...
Hi, in derivable_generator.py, several configurations are listed. However, there is no multi-code configuration for StyleGAN. In fact, StyleGAN's design is different from pggan, where w is inserted into each middle...
