High Resolution Acquisition, Learning and Transfer of Dynamic 3-D Facial Expressions

Simple item page
dc.contributor.authorWang, Yangen_US
dc.contributor.authorHuang, Xiaoleien_US
dc.contributor.authorLee, Chan-Suen_US
dc.contributor.authorZhang, Songen_US
dc.contributor.authorLi, Zhiguoen_US
dc.contributor.authorSamaras, Dimitrisen_US
dc.contributor.authorMetaxas, Dimitrisen_US
dc.contributor.authorElgammal, Ahmeden_US
dc.contributor.authorHuang, Peisenen_US
dc.date.accessioned2015-02-19T09:54:54Z
dc.date.available2015-02-19T09:54:54Z
dc.date.issued2004en_US
dc.description.abstractSynthesis and re-targeting of facial expressions is central to facial animation and often involves significant manual work in order to achieve realistic expressions, due to the difficulty of capturing high quality dynamic expression data. In this paper we address fundamental issues regarding the use of high quality dense 3-D data samples undergoing motions at video speeds, e.g. human facial expressions. In order to utilize such data for motion analysis and re-targeting, correspondences must be established between data in different frames of the same faces as well as between different faces. We present a data driven approach that consists of four parts: 1) High speed, high accuracy capture of moving faces without the use of markers, 2) Very precise tracking of facial motion using a multi-resolution deformable mesh, 3) A unified low dimensional mapping of dynamic facial motion that can separate expression style, and 4) Synthesis of novel expressions as a combination of expression styles. The accuracy and resolution of our method allows us to capture and track subtle expression details. The low dimensional representation of motion data in a unified embedding for all the subjects in the database allows for learning the most discriminating characteristics of each individual's expressions as that person's 'expression style'. Thus new expressions can be synthesized, either as dynamic morphing between individuals, or as expression transfer from a source face to a target face, as demonstrated in a series of experiments.Categories and Subject Descriptors (according to ACM CCS): I.3.7 [Computer Graphics]: Animation; I.3.5 [Computer Graphics]: Curve, surface, solid, and object representations; I.3.3 [Computer Graphics]: Digitizing and scanning; I.2.10 [Artificial intelligence]: Motion ; I.2.10 [Artificial intelligence]: Representations, data structures, and transforms; I.2.10 [Artificial intelligence]: Shape; I.2.6 [Artificial intelligence]: Concept learningen_US
dc.description.number3en_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume23en_US
dc.identifier.doi10.1111/j.1467-8659.2004.00800.xen_US
dc.identifier.issn1467-8659en_US
dc.identifier.pages677-686en_US
dc.identifier.urihttps://doi.org/10.1111/j.1467-8659.2004.00800.xen_US
dc.publisherThe Eurographics Association and Blackwell Publishing, Incen_US
dc.titleHigh Resolution Acquisition, Learning and Transfer of Dynamic 3-D Facial Expressionsen_US
Files
Collections
23-Issue 3