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

dc.contributor.authorKim, SangBinen_US
dc.contributor.authorPark, Inbumen_US
dc.contributor.authorKwon, Seongsuen_US
dc.contributor.authorHan, JungHyunen_US
dc.contributor.editorPanozzo, Daniele and Assarsson, Ulfen_US
dc.date.accessioned2020-05-24T12:53:58Z
dc.date.available2020-05-24T12:53:58Z
dc.date.issued2020
dc.description.abstractMotion 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.en_US
dc.description.number2
dc.description.sectionheadersSynthesizing Gestures, Motion, and Interactions
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.13947
dc.identifier.issn1467-8659
dc.identifier.pages497-507
dc.identifier.urihttps://doi.org/10.1111/cgf.13947
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13947
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.titleMotion Retargetting based on Dilated Convolutions and Skeleton-specific Loss Functionsen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
v39i2pp497-507.pdf
Size:
2.3 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
supple.mp4
Size:
31.96 MB
Format:
Unknown data format
Collections