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:20241205T151900
DTEND;TZID=Asia/Tokyo:20241205T153100
UID:siggraphasia_SIGGRAPH Asia 2024_sess134_papers_816@linklings.com
SUMMARY:I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffu
 sion Models
DESCRIPTION:Technical Papers\n\nWenqi Ouyang (S-Lab for Advanced Intellige
 nce, Nanyang Technological University Singapore); Yi Dong (Nanyang Technol
 ogical University (NTU)); Lei Yang and Jianlou Si (SenseTime); and Xingang
  Pan (S-Lab for Advanced Intelligence, Nanyang Technological University Si
 ngapore)\n\nThe remarkable generative capabilities of diffusion models hav
 e motivated extensive research in both image and video editing. Compared t
 o video editing which faces additional challenges in the time dimension, i
 mage editing has witnessed the development of more diverse, high-quality a
 pproaches and more capable software like Photoshop. In light of this gap, 
 we introduce a novel and generic solution that extends the applicability o
 f image editing tools to videos by propagating edits from a single frame t
 o the entire video using a pre-trained image-to-video model. Our method, d
 ubbed I2VEdit, adaptively preserves the visual and motion integrity of the
  source video depending on the extent of the edits, effectively handling g
 lobal edits, local edits, and moderate shape changes, which existing metho
 ds cannot fully achieve. At the core of our method are two main processes:
  Coarse Motion Extraction to align basic motion patterns with the original
  video, and Appearance Refinement for precise adjustments using fine-grain
 ed attention matching. We also incorporate a skip-interval strategy to mit
 igate quality degradation from auto-regressive generation across multiple 
 video clips. Experimental results demonstrate our framework's superior per
 formance in fine-grained video editing, proving its capability to produce 
 high-quality, temporally consistent outputs.\n\nRegistration Category: Ful
 l Access, Full Access Supporter\n\nLanguage Format: English Language\n\nSe
 ssion Chair: Nanxuan Zhao (Adobe Research)
URL:https://asia.siggraph.org/2024/program/?id=papers_816&sess=sess134
END:VEVENT
END:VCALENDAR