Motion Retargetting based on Dilated Convolutions and Skeleton-specific Loss Functions
- Authors
- Kim, SangBin; Park, Inbum; Kwon, Seongsu; Han, JungHyun
- Issue Date
- 5월-2020
- Publisher
- WILEY
- Keywords
- CCS Concepts; . Computing methodologies -> Neural networks
- Citation
- COMPUTER GRAPHICS FORUM, v.39, no.2, pp.497 - 507
- Indexed
- SCIE
SCOPUS
- Journal Title
- COMPUTER GRAPHICS FORUM
- Volume
- 39
- Number
- 2
- Start Page
- 497
- End Page
- 507
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/56156
- DOI
- 10.1111/cgf.13947
- ISSN
- 0167-7055
- 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.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School > Department of Computer Science and Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.