Rapid one-shot acquisition of dynamic VR avatars

Cited 9 time in webofscience Cited 0 time in scopus
  • Hit : 344
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorMalleson, Charlesko
dc.contributor.authorBazin, Jean-Charlesko
dc.contributor.authorKosek, Maggieko
dc.contributor.authorKlaudiny, Martinko
dc.contributor.authorHuerta, Ivanko
dc.contributor.authorSorkine-Hornung, Alexanderko
dc.contributor.authorMine, Markko
dc.contributor.authorMitchell, Kennyko
dc.date.accessioned2017-09-08T05:34:01Z-
dc.date.available2017-09-08T05:34:01Z-
dc.date.created2017-09-04-
dc.date.created2017-09-04-
dc.date.created2017-09-04-
dc.date.issued2017-04-04-
dc.identifier.citation19th IEEE Virtual Reality, VR 2017, pp.131 - 140-
dc.identifier.issn1087-8270-
dc.identifier.urihttp://hdl.handle.net/10203/225721-
dc.description.abstractWe present a system for rapid acquisition of bespoke, animatable, full-body avatars including face texture and shape. A blendshape rig with a skeleton is used as a template for customization. Identity blendshapes are used to customize the body and face shape at the fitting stage, while animation blendshapes allow the face to be animated. The subject assumes a T-pose and a single snapshot is captured using a stereo RGB plus depth sensor rig. Our system automatically aligns a photo texture and fits the 3D shape of the face. The body shape is stylized according to body dimensions estimated from segmented depth. The face identity blendweights are optimised according to image-based facial landmarks, while a custom texture map for the face is generated by warping the input images to a reference texture according to the facial landmarks. The total capture and processing time is under 10 seconds and the output is a light-weight, game-engine-ready avatar which is recognizable as the subject. We demonstrate our system in a VR environment in which each user sees the other users' animated avatars through a VR headset with real-time audio-based facial animation and live body motion tracking, affording an enhanced level of presence and social engagement compared to generic avatars.-
dc.languageEnglish-
dc.publisherIEEE Computer Society-
dc.titleRapid one-shot acquisition of dynamic VR avatars-
dc.typeConference-
dc.identifier.wosid000403149400018-
dc.identifier.scopusid2-s2.0-85018441730-
dc.type.rimsCONF-
dc.citation.beginningpage131-
dc.citation.endingpage140-
dc.citation.publicationname19th IEEE Virtual Reality, VR 2017-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationManhattan Beach Marriott-
dc.identifier.doi10.1109/VR.2017.7892240-
dc.contributor.localauthorBazin, Jean-Charles-
dc.contributor.nonIdAuthorMalleson, Charles-
dc.contributor.nonIdAuthorKosek, Maggie-
dc.contributor.nonIdAuthorKlaudiny, Martin-
dc.contributor.nonIdAuthorHuerta, Ivan-
dc.contributor.nonIdAuthorSorkine-Hornung, Alexander-
dc.contributor.nonIdAuthorMine, Mark-
dc.contributor.nonIdAuthorMitchell, Kenny-
Appears in Collection
GCT-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 9 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0