Live Face De-Identification in Video

Abstract

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.

ICCV 2019

References in corpus (10)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• mixup: Beyond Empirical Risk Minimization
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces
• DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
• Feature Denoising for Improving Adversarial Robustness
• Face Deidentification with Generative Deep Neural Networks
• Privacy-Protective-GAN for Face De-identification
• On Face Segmentation, Face Swapping, and Face Perception