We propose a neural head reenactment system, which is driven by a latent pose representation and is capable of predicting the foreground segmentation alongside the RGB image. The latent pose representation is learned as a part of the entire reenactment system, and the learning process is based solely on image reconstruction losses. We show that despite its simplicity, with a large and diverse enough training dataset, such learning successfully decomposes pose from identity. The resulting system can then reproduce mimics of the driving person and, furthermore, can perform cross-person reenactment. Additionally, we show that the learned descriptors are useful for other pose-related tasks, such as keypoint prediction and pose-based retrieval.
@article{arxiv.2004.12000,
title = {Neural Head Reenactment with Latent Pose Descriptors},
author = {Egor Burkov and Igor Pasechnik and Artur Grigorev and Victor Lempitsky},
journal= {arXiv preprint arXiv:2004.12000},
year = {2020}
}