CVPR2021

Body2Hands: Learning To Infer 3D Hands From Conversational Gesture Body Dynamics

Evonne Ng, Shiry Ginosar, Trevor Darrell, Hanbyul Joo

Abstract

Figure 1. Hand gestures are vital for conveying non-verbal information. (a) Our work considers how a speaker's upper body alone can facilitate the inference of their hand gestures. (b) From a temporal stack of the speaker's 3D body poses (top), we predict corresponding hands (bottom). (c) Body2Hands outputs a sequence of 3D hand poses in the form of an articulated 3D hand model. Project