Motion Retargetting based on Dilated Convolutions and Skeleton-specific Loss Functions

Sang Bin Kim, Inbum Park, Seongsu Kwon, Jung Hyun Han

Research output: Contribution to journalArticle

Abstract

Motion retargetting refers to the process of adapting the motion of a source character to a target. This paper presents a motion retargetting model based on temporal dilated convolutions. In an unsupervised manner, the model generates realistic motions for various humanoid characters. The retargetted motions not only preserve the high-frequency detail of the input motions but also produce natural and stable trajectories despite the skeleton size differences between the source and target. Extensive experiments are made using a 3D character motion dataset and a motion capture dataset. Both qualitative and quantitative comparisons against prior methods demonstrate the effectiveness and robustness of our method.

Original languageEnglish
Pages (from-to)497-507
Number of pages11
JournalComputer Graphics Forum
Volume39
Issue number2
DOIs
Publication statusPublished - 2020 May 1

Keywords

  • CCS Concepts
  • • Computing methodologies → Neural networks

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'Motion Retargetting based on Dilated Convolutions and Skeleton-specific Loss Functions'. Together they form a unique fingerprint.

  • Cite this