Personalized Animatable Avatars from Depth Data

dc.contributor.authorMashalkar, Jaien_US
dc.contributor.authorBagwe, Niketen_US
dc.contributor.authorChaudhuri, Paragen_US
dc.contributor.editorBetty Mohler and Bruno Raffin and Hideo Saito and Oliver Staadten_US
dc.date.accessioned2014-01-27T11:30:39Z
dc.date.available2014-01-27T11:30:39Z
dc.date.issued2013en_US
dc.description.abstractAbstract We present a method to create virtual character models of real users from noisy depth data. We use a combination of four depth sensors to capture a point cloud model of the person. Direct meshing of this data often creates meshes with topology that is unsuitable for proper character animation. We develop our mesh model by fitting a single template mesh to the point cloud in a two-stage process. The first stage fitting involves piecewise smooth deformation of the mesh, whereas the second stage does a finer fit using an iterative Laplacian framework. We complete the model by adding properly aligned and blended textures to the final mesh and show that it can be easily animated using motion data from a single depth camera. Our process maintains the topology of the original mesh and the proportions of the final mesh match the proportions of the actual user, thus validating the accuracy of the process. Other than the depth sensor, the process does not require any specialized hardware for creating the mesh. It is efficient, robust and is mostly automatic.en_US
dc.description.seriesinformationJoint Virtual Reality Conference of EGVE - EuroVRen_US
dc.identifier.isbn978-3-905674-47-7en_US
dc.identifier.issn1727-530Xen_US
dc.identifier.urihttps://doi.org/10.2312/EGVE.JVRC13.025-032en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectComputer Graphics [I.3.7]en_US
dc.subjectThree Dimensional Graphics and Realismen_US
dc.subjectVirtual Realityen_US
dc.subjectInformation Interfaces and Presentation [H.5.1]en_US
dc.subjectMultimedia Information Systemsen_US
dc.subjectArtificialen_US
dc.subjectaugmenteden_US
dc.subjectand virtual realitiesen_US
dc.titlePersonalized Animatable Avatars from Depth Dataen_US
Files
Original bundle
Now showing 1 - 3 of 3
Loading...
Thumbnail Image
Name:
025-032.pdf
Size:
17.72 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
readme_paper1015.txt
Size:
349 B
Format:
Plain Text
No Thumbnail Available
Name:
video_jvrc2013.avi
Size:
15.67 MB
Format:
Unknown data format