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:20230103T035309Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221207T153000
DTEND;TZID=Asia/Seoul:20221207T170000
UID:siggraphasia_SIGGRAPH Asia 2022_sess163_papers_258@linklings.com
SUMMARY:SCULPTOR: Skeleton-Consistent Face Creation Using a Learned Parame
 tric Generator
DESCRIPTION:Technical Communications, Technical Papers\n\nSCULPTOR: Skelet
 on-Consistent Face Creation Using a Learned Parametric Generator\n\nQiu, L
 i, He, Zhang, Zhang...\n\nRecent years have seen growing interest in 3D hu
 man faces modelling due to its wide applications in digital human, charact
 er generation and animation. Existing approaches overwhelmingly emphasized
  on modeling the exterior shapes, textures and skin properties of faces, i
 gnoring the inherent correlation between inner skeletal structures and app
 earance. In this paper, we present SCULPTOR, 3D face creations with Skelet
 on Consistency Using a Learned Parametric facial generaTOR, aiming to faci
 litate easy creation of both anatomically correct and visually convincing 
 face models via a hybrid parametric-physical representation. At the core o
 f SCULPTOR is LUCY, the first large-scale shape-skeleton face dataset in c
 ollaboration with plastic surgeons. Named after the fossils of one of the 
 oldest known human ancestors, our LUCY dataset contains high-quality Compu
 ted Tomography (CT) scans of the complete human head before and after orth
 ognathic surgeries, critical for evaluating surgery results. LUCY consists
  of 144 scans of 72 subjects (31 male and 41 female) where each subject ha
 s two CT scans taken pre- and post-orthognathic operations.\nBased on our 
 LUCY dataset, we learn a novel skeleton consistent parametric facial gener
 ator, SCULPTOR, which can create the unique and nuanced facial features th
 at help define a character and at the same time maintain physiological sou
 ndness. Our SCULPTOR jointly models the skull, face geometry and face appe
 arance under a unified data-driven framework, by separating the depiction 
 of a 3D face into shape blend shape, pose blend shape and facial expressio
 n blend shape. SCULPTOR preserves both anatomic correctness and visual rea
 lism in facial generation tasks compared with existing methods. Finally, w
 e showcase the robustness and effectiveness of SCULPTOR in various fancy a
 pplications unseen before, like archaeological skeletal facial completion,
  bone-aware character fusion,  skull inference from images, face generatio
 n with lipo-Level change and facial animations, etc.\n\nRegistration Categ
 ory: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERS
 ON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_258&sess=sess16
 3
END:VEVENT
END:VCALENDAR