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:20250110T023312Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241204T131100
DTEND;TZID=Asia/Tokyo:20241204T132300
UID:siggraphasia_SIGGRAPH Asia 2024_sess116_papers_884@linklings.com
SUMMARY:InstantDrag: Improving Interactivity in Drag-based Image Editing
DESCRIPTION:Technical Papers\n\nJoonghyuk Shin (Seoul National University)
 , Daehyeon Choi (POSTECH), and Jaesik Park (Seoul National University)\n\n
 Drag-based image editing has recently gained popularity for its interactiv
 ity and precision. However, despite the ability of text-to-image models to
  generate samples within a second, drag editing still lags behind due to t
 he challenge of accurately reflecting user interaction while maintaining i
 mage content. Some existing approaches rely on computationally intensive p
 er-image optimization or intricate guidance-based methods, requiring addit
 ional inputs such as masks for movable regions and text prompts, thereby c
 ompromising the interactivity of the editing process. We introduce Instant
 Drag, an optimization-free pipeline that enhances interactivity and speed,
  requiring only an image and a drag instruction as input. InstantDrag cons
 ists of two carefully designed networks: a drag-conditioned optical flow g
 enerator (FlowGen) and an optical flow-conditioned diffusion model (FlowDi
 ffusion). InstantDrag learns motion dynamics for drag-based image editing 
 in real-world video datasets by decomposing the task into motion generatio
 n and motion-conditioned image generation. We demonstrate InstantDrag's ca
 pability to perform fast, photo-realistic edits without masks or text prom
 pts through experiments on facial video datasets and general scenes. These
  results highlight the efficiency of our approach in handling drag-based i
 mage editing, making it a promising solution for interactive, real-time ap
 plications.\n\nRegistration Category: Full Access, Full Access Supporter\n
 \nLanguage Format: English Language\n\nSession Chair: Dani Lischinski (Heb
 rew University of Jerusalem, Google)
URL:https://asia.siggraph.org/2024/program/?id=papers_884&sess=sess116
END:VEVENT
END:VCALENDAR