BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:Asia/Seoul X-LIC-LOCATION:Asia/Seoul BEGIN:STANDARD TZOFFSETFROM:+0900 TZOFFSETTO:+0900 TZNAME:KST DTSTART:18871231T000000 DTSTART:19881009T020000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230103T035307Z LOCATION:Auditorium\, Level 5\, West Wing DTSTART;TZID=Asia/Seoul:20221206T100000 DTEND;TZID=Asia/Seoul:20221206T120000 UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_258@linklings.com SUMMARY:SCULPTOR: Skeleton-Consistent Face Creation Using a Learned Parame tric Generator DESCRIPTION:Technical Papers\n\nSCULPTOR: Skeleton-Consistent Face Creatio n Using a Learned Parametric Generator\n\nQiu, Li, He, Zhang, Zhang...\n\n Recent years have seen growing interest in 3D human faces modelling due to its wide applications in digital human, character generation and animatio n. Existing approaches overwhelmingly emphasized on modeling the exterior shapes, textures and skin properties of faces, ignoring the inherent corre lation between inner skeletal structures and appearance. In this paper, we present SCULPTOR, 3D face creations with Skeleton Consistency Using a Lea rned Parametric facial generaTOR, aiming to facilitate easy creation of bo th anatomically correct and visually convincing face models via a hybrid p arametric-physical representation. At the core of SCULPTOR is LUCY, the fi rst large-scale shape-skeleton face dataset in collaboration with plastic surgeons. Named after the fossils of one of the oldest known human ancesto rs, our LUCY dataset contains high-quality Computed Tomography (CT) scans of the complete human head before and after orthognathic surgeries, critic al for evaluating surgery results. LUCY consists of 144 scans of 72 subjec ts (31 male and 41 female) where each subject has two CT scans taken pre- and post-orthognathic operations.\nBased on our LUCY dataset, we learn a n ovel skeleton consistent parametric facial generator, SCULPTOR, which can create the unique and nuanced facial features that help define a character and at the same time maintain physiological soundness. Our SCULPTOR joint ly models the skull, face geometry and face appearance under a unified dat a-driven framework, by separating the depiction of a 3D face into shape bl end shape, pose blend shape and facial expression blend shape. SCULPTOR pr eserves both anatomic correctness and visual realism in facial generation tasks compared with existing methods. Finally, we showcase the robustness and effectiveness of SCULPTOR in various fancy applications unseen before, like archaeological skeletal facial completion, bone-aware character fusi on, skull inference from images, face generation with lipo-Level change a nd facial animations, etc.\n\nRegistration Category: FULL ACCESS, EXPERIEN CE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\ nFormat: IN-PERSON URL:https://sa2022.siggraph.org/en/full-program/?id=papers_258&sess=sess15 3 END:VEVENT END:VCALENDAR