To transfer the motion, we extract poses from the source subject and apply the learned pose-to-appearance mapping to generate the target subject. We approach this problem as video-to-video translation using pose as an intermediate representation. In addition, we release a first-of-its-kind open-source dataset of videos that can be legally used for training and motion transfer.This paper presents a simple method for 'do as I do' motion transfer: given a source video of a person dancing, we can transfer that performance to a novel (amateur) target after only a few minutes of the target subject performing standard moves. This motivates us to also provide a forensics tool for reliable synthetic content detection, which is able to distinguish videos synthesized by our system from real data. Although our method is quite simple, it produces surprisingly compelling results (see video). We predict two consecutive frames for temporally coherent video results and introduce a separate pipeline for realistic face synthesis. This paper presents a simple method for 'do as I do' motion transfer: given a source video of a person dancing, we can transfer that performance to a novel (amateur) target after only a few minutes of the target subject performing standard moves.

Everybody dance now piano