Kernel Projection of Latent Structures Regression for Facial Animation Retargeting

dc.contributor.authorOuzounis, Christosen_US
dc.contributor.authorKilias, Alexen_US
dc.contributor.authorMousas, Christosen_US
dc.contributor.editorFabrice Jaillet and Florence Zaraen_US
dc.date.accessioned2017-04-22T17:18:19Z
dc.date.available2017-04-22T17:18:19Z
dc.date.issued2017
dc.description.abstractInspired by kernel methods that have been used extensively in achieving efficient facial animation retargeting, this paper presents a solution to retargeting facial animation in virtual character's face model based on the kernel projection of latent structure (KPLS) regression between semantically similar facial expressions. Specifically, a given number of corresponding semantically similar facial expressions are projected into the latent space. By using the Nonlinear Iterative Partial Least Square method, decomposition of the latent variables is achieved. Finally, the KPLS is achieved by solving a kernalized version of the eigenvalue problem. By evaluating our methodology with other kernel-based solutions, the efficiency of the presented methodology in transferring facial animation to face models with different morphological variations is demonstrated.en_US
dc.description.sectionheadersSession 3
dc.description.seriesinformationWorkshop on Virtual Reality Interaction and Physical Simulation
dc.identifier.doi10.2312/vriphys.20171084
dc.identifier.isbn978-3-03868-032-1
dc.identifier.pages59-65
dc.identifier.urihttps://doi.org/10.2312/vriphys.20171084
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vriphys20171084
dc.publisherThe Eurographics Associationen_US
dc.subjectI.3.7 [Computer Graphics]
dc.subjectThree DimensionalGraphics and Realism
dc.subjectAnimation
dc.titleKernel Projection of Latent Structures Regression for Facial Animation Retargetingen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
059-065.pdf
Size:
16.29 MB
Format:
Adobe Portable Document Format
Collections