Live Face De-Identification in Video

By Oran Gafni, Lior Wolf, Yaniv Taigman. 2019

158 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors (2022, methodology): “[15] introduced face-reﬁnement to SPADE through a pre-trained face-embedding network inspired by face-generation methods [16].”
Face identity disentanglement via latent space mapping (2020, methodology): “This is in contrast to previous methods [Gafni et al. 2019], that performminimal facial modification to fool face recognition methods.”
CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks (2020, methodology): “In this section, we compare the de-identiﬁcation (anonymization) power of our model compared to state-of-the-art [7].”
Disentangling in Latent Space by Harnessing a Pretrained Generator (2020, methodology): “remove the face from the target image and complete it using a GAN [54], while other methods [19, 61] shift the identity using a pre-trained face recognition network, while keeping the general image relatively similar to the source.”