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:20230103T035306Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_398@linklings.com
SUMMARY:FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstru
 ction and Expression Editing
DESCRIPTION:Technical Papers\n\nFDNeRF: Few-shot Dynamic Neural Radiance F
 ields for Face Reconstruction and Expression Editing\n\nZHANG, LI, WAN, WA
 NG, LIAO\n\nWe propose a Few-shot Dynamic Neural Radiance Field (FDNeRF), 
 the first NeRF-based method capable of reconstruction and expression editi
 ng of 3D faces based on a small number of dynamic images. Unlike existing 
 dynamic NeRFs that require dense images as input and can only be modeled f
 or a single identity, our method enables face reconstruction across differ
 ent persons with few-shot inputs. Compared to state-of-the-art few-shot Ne
 RFs designed for modeling static scenes, the proposed FDNeRF accepts view-
 inconsistent dynamic inputs and supports arbitrary facial expression editi
 ng, i.e., producing faces with novel expressions beyond the input ones. To
  handle the inconsistencies between dynamic inputs, we introduce a well-de
 signed conditional feature warping (CFW) module to perform expression cond
 itioned warping in 2D feature space, which is also identity adaptive and 3
 D constrained. As a result, features of different expressions are transfor
 med into the target ones. We then construct a radiance field based on thes
 e view-consistent features and use volumetric rendering to synthesize nove
 l views of the modeled faces. Extensive experiments with quantitative and 
 qualitative evaluation demonstrate that our method outperforms existing dy
 namic and few-shot NeRFs on both 3D face reconstruction and expression edi
 ting tasks. Code is available at https://github.com/FDNeRF/FDNeRF.\n\nRegi
 stration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS,
  TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_398&sess=sess15
 3
END:VEVENT
END:VCALENDAR