• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Do as we do: Multiple Person Video-to-Video Transfer
 
  • Details
  • Full
Options
2021
Conference Paper
Titel

Do as we do: Multiple Person Video-to-Video Transfer

Abstract
Our goal is to transfer the motion of real people from a source video to a target video with realistic results. While recent advances significantly improved image-to-image translations, only few works account for body motions and temporal consistency. However, those focus only on video retargeting for a single actor/ for single actors. In this work, we propose a marker-less approach for multiple-person video-to-video transfer using pose as an intermediate representation. Given a source video with multiple persons dancing or working out, our method transfers the body motion of all actors to a new set of actors in a different video. Differently from recent"" do as I do"" methods, we focus specifically on transferring multiple person at the same time and tackle the related identity switch problem. Our method is able to convincingly transfer body motion to the target video, while preserving specific features of the target video, such as feet touching the floor and relative position of the actors. The evaluation is performed with visual quality and appearance metrics using publicly available videos with the permission of their owners.
Author(s)
Cormier, Mickael
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Mortazavi Moshkenan, Houraalsadat
Lörch, Franz
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Metzler, Jürgen
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Beyerer, Jürgen
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Hauptwerk
IEEE 4th International Conference on Multimedia Information Processing and Retrieval, MIPR 2021
Konferenz
International Conference on Multimedia Information Processing and Retrieval (MIPR) 2021
Thumbnail Image
DOI
10.1109/MIPR51284.2021.00020
Language
English
google-scholar
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Tags
  • GaN

  • motion transfer

  • video-to-video transf...

  • video retargeting

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022