Open rohitsaluja22 opened 6 years ago
You can basically use any existing image translation GANs, for example pix2pix: https://github.com/phillipi/pix2pix If you want to make it WGAN-based, you just need to substitute its loss function with a WGAN loss.
Hi, please share a WGAN code to convert synthetic images to real (with paired images) if you know. Any other vanila GAN would also be helpful.