Also the model is trained on faces, not backgrounds. Pretty soon we’re going to ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		jcims on Nov 14, 2022 \| parent \| context \| favorite \| on: Which face is real? Also the model is trained on faces, not backgrounds. Pretty soon we’re going to see entire 3D scenes generated and rendered photorealistically through a camera model.

relaxing on Nov 14, 2022 [–]

I don't think that's true. If they masked out the backgrounds on training, how would the model be able to synthesize a background at all?

The problem is there's too much variety in the backgrounds of the training set. They don't follow a pattern the way growing a human does.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact