Sounds great on paper but
Tsardoz opened this issue · 1 comments
Tsardoz commented
omriav commented
Hi,
It was never claimed in the paper that this method will be able to generate a plausible output for any inputs.
In this example, adding a person to the desired place is very hard, if you use a different image that a person can
more naturally fit - you will get a better result. For example:
Predictions:
In addition, generating people is a hard task in general as you can see.