From motion capture to action capture: A review of imitation learning techniques and their application to VR-based character animation

Bernhard Jung, Hani Ben Amor, Guido Heumer, Matthias Weber

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Citations (Scopus)

Abstract

We present a novel method for virtual character animation that we call action capture. In this approach, virtual characters learn to imitate the actions of Virtual Reality (VR) users by tracking not only the users' movements but also their interactions with scene objects.Action capture builds on conventional motion capture but differs from it in that higher-level action representations are transferred rather than low-level motion data. As an advantage, the learned actions can often be naturally applied to varying situations, thus avoiding retargetting problems of motion capture. The idea of action capture is inspired by human imitation learning; related methods have been investigated for a longer time in robotics. The paper reviews the relevant literature in these areas before framing the concept of action capture in the context of VR-based character animation. We also present an example in which the actions of a VR user are transferred to a virtual worked.

Original languageEnglish (US)
Title of host publicationProceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST
Pages145-154
Number of pages10
DOIs
StatePublished - 2006
Externally publishedYes
Event13th ACM Symposium Virtual Reality Software and Technology, VRST'06 - Limassol, Cyprus
Duration: Nov 1 2006 → Nov 3 2006

Other

Other13th ACM Symposium Virtual Reality Software and Technology, VRST'06
CountryCyprus
CityLimassol
Period11/1/06 → 11/3/06

Fingerprint

Animation
Virtual reality
Robotics

Keywords

  • Action capture
  • Character animation
  • Imitation learning
  • Motion capture
  • Virtual reality

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Jung, B., Ben Amor, H., Heumer, G., & Weber, M. (2006). From motion capture to action capture: A review of imitation learning techniques and their application to VR-based character animation. In Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST (pp. 145-154) https://doi.org/10.1145/1180495.1180526

From motion capture to action capture : A review of imitation learning techniques and their application to VR-based character animation. / Jung, Bernhard; Ben Amor, Hani; Heumer, Guido; Weber, Matthias.

Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST. 2006. p. 145-154.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Jung, B, Ben Amor, H, Heumer, G & Weber, M 2006, From motion capture to action capture: A review of imitation learning techniques and their application to VR-based character animation. in Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST. pp. 145-154, 13th ACM Symposium Virtual Reality Software and Technology, VRST'06, Limassol, Cyprus, 11/1/06. https://doi.org/10.1145/1180495.1180526
Jung B, Ben Amor H, Heumer G, Weber M. From motion capture to action capture: A review of imitation learning techniques and their application to VR-based character animation. In Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST. 2006. p. 145-154 https://doi.org/10.1145/1180495.1180526
Jung, Bernhard ; Ben Amor, Hani ; Heumer, Guido ; Weber, Matthias. / From motion capture to action capture : A review of imitation learning techniques and their application to VR-based character animation. Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST. 2006. pp. 145-154
@inproceedings{0de258e954cc403e926d7c56259009c8,
title = "From motion capture to action capture: A review of imitation learning techniques and their application to VR-based character animation",
abstract = "We present a novel method for virtual character animation that we call action capture. In this approach, virtual characters learn to imitate the actions of Virtual Reality (VR) users by tracking not only the users' movements but also their interactions with scene objects.Action capture builds on conventional motion capture but differs from it in that higher-level action representations are transferred rather than low-level motion data. As an advantage, the learned actions can often be naturally applied to varying situations, thus avoiding retargetting problems of motion capture. The idea of action capture is inspired by human imitation learning; related methods have been investigated for a longer time in robotics. The paper reviews the relevant literature in these areas before framing the concept of action capture in the context of VR-based character animation. We also present an example in which the actions of a VR user are transferred to a virtual worked.",
keywords = "Action capture, Character animation, Imitation learning, Motion capture, Virtual reality",
author = "Bernhard Jung and {Ben Amor}, Hani and Guido Heumer and Matthias Weber",
year = "2006",
doi = "10.1145/1180495.1180526",
language = "English (US)",
isbn = "1595933212",
pages = "145--154",
booktitle = "Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST",

}

TY - GEN

T1 - From motion capture to action capture

T2 - A review of imitation learning techniques and their application to VR-based character animation

AU - Jung, Bernhard

AU - Ben Amor, Hani

AU - Heumer, Guido

AU - Weber, Matthias

PY - 2006

Y1 - 2006

N2 - We present a novel method for virtual character animation that we call action capture. In this approach, virtual characters learn to imitate the actions of Virtual Reality (VR) users by tracking not only the users' movements but also their interactions with scene objects.Action capture builds on conventional motion capture but differs from it in that higher-level action representations are transferred rather than low-level motion data. As an advantage, the learned actions can often be naturally applied to varying situations, thus avoiding retargetting problems of motion capture. The idea of action capture is inspired by human imitation learning; related methods have been investigated for a longer time in robotics. The paper reviews the relevant literature in these areas before framing the concept of action capture in the context of VR-based character animation. We also present an example in which the actions of a VR user are transferred to a virtual worked.

AB - We present a novel method for virtual character animation that we call action capture. In this approach, virtual characters learn to imitate the actions of Virtual Reality (VR) users by tracking not only the users' movements but also their interactions with scene objects.Action capture builds on conventional motion capture but differs from it in that higher-level action representations are transferred rather than low-level motion data. As an advantage, the learned actions can often be naturally applied to varying situations, thus avoiding retargetting problems of motion capture. The idea of action capture is inspired by human imitation learning; related methods have been investigated for a longer time in robotics. The paper reviews the relevant literature in these areas before framing the concept of action capture in the context of VR-based character animation. We also present an example in which the actions of a VR user are transferred to a virtual worked.

KW - Action capture

KW - Character animation

KW - Imitation learning

KW - Motion capture

KW - Virtual reality

UR - http://www.scopus.com/inward/record.url?scp=34547467245&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547467245&partnerID=8YFLogxK

U2 - 10.1145/1180495.1180526

DO - 10.1145/1180495.1180526

M3 - Conference contribution

SN - 1595933212

SN - 9781595933218

SP - 145

EP - 154

BT - Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST

ER -

Access to Document