Temporally coherent video anonymization through GAN inpainting

Understand

This work tackles the problem of temporally coherent face anonymization in natural video streams.We propose JaGAN, a two-stage system starting with detecting and masking out faces with black image patches in all individual frames of the video.

• The second stage leverages a privacy-preserving Video Generative Adversarial Network designed to inpaint the missing image patches with artificially generated faces.
• Our initial experiments reveal that image based generative models are not capable of inpainting patches showing temporal coherent appearance across neighboring video frames.
• To address this issue we introduce a newly curated video collection, which is made publicly available for the research community along with this paper.