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_346@linklings.com SUMMARY:VideoReTalking: Audio-based Lip Synchronization for Talking Head V ideo Editing In the Wild DESCRIPTION:Technical Papers\n\nVideoReTalking: Audio-based Lip Synchroniz ation for Talking Head Video Editing In the Wild\n\nCheng, Cun, Zhang, Xia , Yin...\n\nWe present VideoReTalking, a new system to edit the faces of a real-world talking head video according to an input audio, producing a hi gh-quality and lip-syncing output video even with a different emotion.Our system disentangles this objective into three sequential tasks: (1) face v ideo generation with a canonical expression; (2) audio-driven lip-sync; an d (3) face enhancement for improving photo-realism. Given a talking-head v ideo, we first modify the expression of each frame according to the same e xpression template using the expression editing network, resulting in a vi deo with the canonical expression. This video, together with a given audio , are then fed into the lip-sync network to generate a lip-syncing video. Finally, we improve the photo-realism of the synthesized faces through an identity-aware face enhancement network and post-processing. We use learni ng-based approaches for all three steps and all our modules can be tackled in a sequential pipeline without any user intervention. Furthermore, our system is a generic approach that is not retrained to a specific video or person. \nEvaluations on two widely-used datasets and in-the-wild examples demonstrate the superiority of our framework over other state-of-the-art methods in terms of lip-sync accuracy and visual quality.\n\nRegistration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EX HIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON URL:https://sa2022.siggraph.org/en/full-program/?id=papers_346&sess=sess15 3 END:VEVENT END:VCALENDAR