BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171531Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T145600
DTEND;TZID=Asia/Tokyo:20241205T150800
UID:siggraphasia_SIGGRAPH Asia 2024_sess134_papers_561@linklings.com
SUMMARY:Fashion-VDM: Video Diffusion Model for Virtual Try-On
DESCRIPTION:Johanna Karras (Google Research, University of Washington); Yi
 ngwei Li and Nan Liu (Google Research); Luyang Zhu (Google Research, Unive
 rsity of Washington); Innfarn Yoo, Andreas Lugmayr, and Chris Lee (Google 
 Research); and Ira Kemelmacher-Shlizerman (Google Research, University of 
 Washington)\n\nWe present Fashion-VDM, a video diffusion model (VDM) for g
 enerating virtual try-on videos. Given an input garment image and person v
 ideo, our method aims to generate a high-quality try-on video of the perso
 n wearing the given garment, while preserving the person's identity and mo
 tion. Image-based virtual try-on has shown impressive results; however, ex
 isting video virtual try-on (VVT) methods are still lacking garment detail
 s and temporal consistency. To address these issues, we propose a diffusio
 n-based architecture for video virtual try-on, split classifier-free guida
 nce for increased control over the conditioning inputs, and a progressive 
 temporal training strategy for single-pass 64-frame, 512px video generatio
 n. We also demonstrate the effectiveness of joint image-video training for
  video try-on, especially when video data is limited. Our qualitative and 
 quantitative experiments show that our approach sets the new state-of-the-
 art for video virtual try-on.\n\nRegistration Category: Full Access, Full 
 Access Supporter\n\nLanguage Format: English Language\n\nSession Chair: Na
 nxuan Zhao (Adobe Research)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_561&sess=sess134
END:VEVENT
END:VCALENDAR
