Facile: a System for Artificial Face Dataset Generation

dc.contributor.authorBrambilla, Andreaen_US
dc.contributor.authorColombo, Alessandroen_US
dc.contributor.editorEnrico Puppo and Andrea Brogni and Leila De Florianien_US
dc.date.accessioned2014-01-27T16:34:10Z
dc.date.available2014-01-27T16:34:10Z
dc.date.issued2010en_US
dc.description.abstractWe present Facile, a system for the generation of artificial face datasets aimed to assist the training and evaluation phases of face related algorithms. Facile is able to generate, starting from a set of textured 3D faces with neutral expressions, a new dataset containing synthesized facial expressions, multiple viewpoint positions and lighting conditions. The system is featured by a facial animation algorithm based on a mass-spring system. Muscles, defined on a reference face, modify springs contractions when activated. Dense correspondence with the reference face is computed for each input face: in this way muscles are automatically positioned and the desired facial expression is generated through physical simulation. Output images can be rendered with different lighting conditions and viewpoint positions depending on the task requirements.en_US
dc.description.seriesinformationEurographics Italian Chapter Conference 2010en_US
dc.identifier.isbn978-3-905673-80-7en_US
dc.identifier.urihttps://doi.org/10.2312/LocalChapterEvents/ItalChap/ItalianChapConf2010/073-079en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectCategories and Subject Descriptors (according to ACM CCS): Face Modeling; Mass spring systems; Facial expressions.en_US
dc.titleFacile: a System for Artificial Face Dataset Generationen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
073-079.pdf
Size:
666.3 KB
Format:
Adobe Portable Document Format