2019/11/19 by Oran Gafni, Lior Wolf, Yaniv Taigman · 1 citation
Computer Science · Mathematics · #cs.LG #cs.CV #cs.GR #stat.ML
published as Proceedings of the IEEE International Conference on Computer Vision (2019) 9378--9387 · ICCV 2019
arxiv created 2019/11/19 · arxiv updated 2019/11/20
We propose a method for face de-identification that enables fully automatic video modification at high frame rates. The goal is to maximally decorrelate the identity, while having the perception (pose, illumination and expression) fixed. We achieve this by a novel feed-forward encoder-decoder network architecture that is conditioned on the high-level representation of a person's facial image. The network is global, in the sense that it does not need to be retrained for a given video or for a given identity, and it creates natural looking image sequences with little distortion in time.