Everybody Dance Now
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. We pose this problem as a per-frame image-to-image translation with spatio-temporal smoothing. Using pose detections as an intermediate representation between source and target, we learn a mapping from pose images to a target subject's appearance. We adapt this setup for temporally coherent video generation including realistic face synthesis. Our video demo can be found here.
||Everybody Dance Now
Caroline Chan, Shiry Ginosar, Tinghui Zhou, Alexei A. Efros
[hosted on arXiv]
This work was supported, in part, by NSF grant IIS-1633310 and research gifts from Adobe, eBay, and Google. This webpage template was borrowed from here.