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_381@linklings.com
SUMMARY:Neural Parameterization for Dynamic Human Head Editing
DESCRIPTION:Technical Papers\n\nNeural Parameterization for Dynamic Human 
 Head Editing\n\nMa, Li, Liao, Wang, Zhang...\n\nImplicit radiance function
 s emerged as a powerful scene representation for reconstructing and render
 ing photo-realistic views of a 3D scene. These representations, however, s
 uffer from poor editability. On the other hand, explicit representations s
 uch as polygonal meshes allow easy editing, but are not as suitable for re
 constructing accurate details in dynamic human heads, such as fine facial 
 features, hair, and eyes. In this work, we present Neural Parameterization
  (NeP), a hybrid representation that provides the advantages of both impli
 cit and explicit methods. NeP is capable of photo-realistic rendering whil
 e allowing fine-grained editing of the scene geometry and appearance. We f
 irst disentangle the geometry and appearance by parameterizing the 3D geom
 etry into 2D texture space. We enable geometric editability by introducing
  an explicit linear deformation blending layer. The deformation is control
 led by a set of sparse key points which can be explicitly and intuitively 
 displaced to edit the geometry. For appearance, we develop a hybrid 2D tex
 ture consisting of an explicit texture map for easy editing and implicit v
 iew and time-dependent residuals to model temporal and view variations. We
  compare our method to several reconstruction and editing baselines. The r
 esults show that the NeP achieves almost the same level of rendering accur
 acy while maintaining high editability.\n\nRegistration Category: FULL ACC
 ESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguag
 e: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_381&sess=sess15
 3
END:VEVENT
END:VCALENDAR