News for hackers. Stuff that matters.

A comment on Text to Photo-Realistic Image Synthesis with Generative Adversarial Networks.

Re:Text to Photo-Realistic Image Synthesis with Generative A... by grownseed on Friday October 20, 2017 @05:24PM (#15519201)
The Github page shows a nice overview and some examples: https://github.com/hanzhanggit/StackGAN. Interestingly it seems to struggle with the birds' legs (e.g. merging them with branches, blurring them or just not generating them). Is this is a problem with the size of the feature or the colors or ...? I know very little about this field but I find it fascinating.
[ Parent | on HN ]
Re:Text to Photo-Realistic Image Synthesis with Generative A... by bmsleight_ on Saturday October 21, 2017 @03:29AM (#15521044)
The Appendix of the pdf - https://arxiv.org/pdf/1612.03242 has more examples, including living rooms.
[ Parent | on HN ]