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:20230103T035311Z
LOCATION:Room 324\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221208T153000
DTEND;TZID=Asia/Seoul:20221208T170000
UID:siggraphasia_SIGGRAPH Asia 2022_sess166_papers_346@linklings.com
SUMMARY:VideoReTalking: Audio-based Lip Synchronization for Talking Head V
 ideo Editing In the Wild
DESCRIPTION:Technical Communications, Technical Papers\n\nVideoReTalking: 
 Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
 \n\nCheng, Cun, Zhang, Xia, Yin...\n\nWe present VideoReTalking, a new sys
 tem to edit the faces of a real-world talking head video according to an i
 nput audio, producing a high-quality and lip-syncing output video even wit
 h a different emotion.Our system disentangles this objective into three se
 quential tasks: (1) face video generation with a canonical expression; (2)
  audio-driven lip-sync; and (3) face enhancement for improving photo-reali
 sm. Given a talking-head video, we first modify the expression of each fra
 me according to the same expression template using the expression editing 
 network, resulting in a video with the canonical expression. This video, t
 ogether with a given audio, are then fed into the lip-sync network to gene
 rate a lip-syncing video. Finally, we improve the photo-realism of the syn
 thesized faces through an identity-aware face enhancement network and post
 -processing. We use learning-based approaches for all three steps and all 
 our modules can be tackled in a sequential pipeline without any user inter
 vention. Furthermore, our system is a generic approach that is not retrain
 ed to a specific video or person. \nEvaluations on two widely-used dataset
 s and in-the-wild examples demonstrate the superiority of our framework ov
 er other state-of-the-art methods in terms of lip-sync accuracy and visual
  quality.\n\nRegistration Category: FULL ACCESS, ON-DEMAND ACCESS\n\nLangu
 age: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_346&sess=sess16
 6
END:VEVENT
END:VCALENDAR