Conversation

@andy_matuschak

Quite a striking result. Given a camera mounted in one’s glasses, pointed at one’s face, this system can synthesize the view of a camera in *front* of you, pointed at you. You could video chat while walking around without holding anything in front of you. youtube.com/watch?v=atzPvW

15

115

472

Tanishq Kancharla (tk)

that’s crazy to me. There must be more behind the scenes bc the hair is invisible in the input but perfectly generated in the outputs

1

@andy_matuschak

Replying to

It requires per-subject training, which presumably conditions the hair.

1:29 AM · Nov 19, 2020TweetDeck

@PrintsCharming

Replying to

@andy_matuschak

and

I see what you did there.

3