BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030653Z
LOCATION:Meeting Room S423+S424\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251216T110100
DTEND;TZID=Asia/Hong_Kong:20251216T111200
UID:siggraphasia_SIGGRAPH Asia 2025_sess117_papers_1422@linklings.com
SUMMARY:Learning to Refocus with Video Diffusion Models
DESCRIPTION:SaiKiran Tedla (Adobe, York University) and Zhoutong Zhang, Xu
 aner Zhang, and Shumian Xin (Adobe)\n\nFocus is a cornerstone of photograp
 hy, yet autofocus systems often fail to capture the intended subject, and 
 users frequently wish to adjust focus after capture. We introduce a novel 
 method for realistic post-capture refocusing using video diffusion models.
  From a single defocused image, our approach generates a perceptually accu
 rate focal stack, represented as a video sequence, enabling interactive re
 focusing and unlocking a range of downstream applications. We release a la
 rge-scale focal stack dataset acquired under diverse real-world smartphone
  conditions to support this work and future research. Our method consisten
 tly outperforms existing approaches in both perceptual quality and robustn
 ess across challenging scenarios, paving the way for more advanced focus-e
 diting capabilities in everyday photography.\n\nRegistration Category: Ful
 l Access, Full Access Supporter\n\nSession Chair: Qiang Fu (King Abdullah 
 University of Science and Technology (KAUST))\n\n
END:VEVENT
END:VCALENDAR