News for hackers. Stuff that matters.

A comment on PixelNN – Example-Based Image Synthesis.

Re:PixelNN – Example-Based Image Synthesis by imaginenore on Monday September 25, 2017 @06:50AM (#15329367)
It almost looks like they mixed training and testing data in some of the examples. The bottom-left sample in the normals-to-faces is extremely suspicions.
[ Parent | on HN ]
Re:PixelNN – Example-Based Image Synthesis by jj12345 on Monday September 25, 2017 @08:30AM (#15329833)
I was looking at this as well, but I'm willing to suspend my disbelief because the normal vaguely looks like it has a good deal of information (in a basic fidelity sense).
[ Parent | on HN ]
Re:PixelNN – Example-Based Image Synthesis by jameshart on Monday September 25, 2017 @10:23AM (#15330716)
seems astonishing that the normal information includes enough detail to tell you which direction the eyes are pointing, though?
[ Parent | on HN ]