Closed hao-pt closed 1 year ago
Thanks for reading our paper :) We haven't tested our model on noise to data tasks yet, as our focus was making SB work on unpaired image-to-image tasks. But, we expect similar performance as DDGAN (https://arxiv.org/abs/2112.07804) as our model is based on the DDGAN framework. We will update the repo when we get some results on unconditional generation.
Firstly, it is a great work that helps me catch up with SB concept. Anw, I am quite curious whether your method can be applied to standard image generation from pure noise. Have you tried it before, it is highly appreciated if you can share some trial results.