ML Anthology

Neural Head Reenactment with Latent Pose Descriptors

Egor Burkov, Igor Pasechnik, Artur Grigorev, Victor Lempitsky
CVPR 2020
doi:10.1109/CVPR42600.2020.01380 /cvpr/2020/burkov2020cvpr-neural/

Abstract

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.

PDF CVPR Semantic Scholar

Cite

Text

Burkov et al. "Neural Head Reenactment with Latent Pose Descriptors." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.01380

Markdown

[Burkov et al. "Neural Head Reenactment with Latent Pose Descriptors." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/burkov2020cvpr-neural/) doi:10.1109/CVPR42600.2020.01380

BibTeX

@inproceedings{burkov2020cvpr-neural,
  title     = {{Neural Head Reenactment with Latent Pose Descriptors}},
  author    = {Burkov, Egor and Pasechnik, Igor and Grigorev, Artur and Lempitsky, Victor},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.01380},
  url       = {https://mlanthology.org/cvpr/2020/burkov2020cvpr-neural/}
}