Srinivas Rao1    Rodrigo Ortiz-Cayon1    Matteo Munaro1    Aidas Liaudanskas1    Krunal Chande1

Tobias Bertel2    Christian Richardt2    Alexander J. B. Trevor3    Stefan Holzer1    Abhishek Kar4

1 Fyusion Inc.       2 University of Bath       3 Robust.AI       4 Google Inc.

Poster at SIGGRAPH Asia 2020


Abstract

We propose a system for free-viewpoint facial re-enactment from a casual video capture of a target subject. Our system can render and re-enact the subject consistently in all the captured views. Furthermore, our system also enables interactive free-viewpoint facial re-enactment of the target from novel views. The re-enactment of the target subject is driven by an expression sequence of a source subject, which is captured using a custom app running on an iPhone X. Our system handles large pose variations in the target subject while keeping the re-enactment consistent. We demonstrate the efficacy of our system by showing various applications.

Downloads

Bibtex

@InProceedings{HoloBot,
  author    = {Srinivas Rao and Rodrigo Ortiz-Cayon and Matteo Munaro and Aidas Liaudanskas and Krunal Chande and Tobias Bertel and Christian Richardt and Alexander J. B. Trevor and Stefan Holzer and Abhishek Kar},
  title     = {Free-Viewpoint Facial Re-Enactment from a Casual Capture},
  booktitle = {SIGGRAPH Asia Posters},
  year      = {2020},
  doi       = {10.1145/3415264.3425453},
  url       = {https://richardt.name/holobot/},
}