arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1911.08348cs.LGcs.CVcs.GRstat.ML
收藏

视频中的人脸去识别

Live Face De-Identification in Video

Facebook AI Research(脸书人工智能研究院);Tel-Aviv University(特拉维夫大学)

Oran Gafni, Lior Wolf, Yaniv Taigman

摘要:

我们提出了一种人脸去识别的方法,使全自动视频修改在高帧速率。我们的目标是最大限度地去相关的身份,同时有固定的感知(姿势,照明和表情)。我们通过一种新颖的前馈编码器-解码器网络架构来实现这一点,该架构以人的面部图像的高级表示为条件。该网络是全球性的,从某种意义上说,它不需要针对给定的视频或给定的身份进行重新训练,并且它可以创建自然的图像序列,并且在时间上几乎没有失真。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑