BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070241Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_345@linklings.com
SUMMARY:Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
DESCRIPTION:Technical Papers\n\nShuai Yang, Yifan Zhou, Ziwei Liu, and Che
 n Change Loy (Nanyang Technological University, Singapore)\n\nLarge text-t
 o-image diffusion models have exhibited impressive proficiency in generati
 ng high-quality images. However, when applying these models to video domai
 n, ensuring temporal consistency across video frames remains a formidable 
 challenge.\nThis paper proposes a novel zero-shot text-guided video-to-vid
 eo translation framework to adapt image models to videos. The framework in
 cludes two parts: key frame translation and full video translation. The fi
 rst part uses an adapted diffusion model to generate key frames, with hier
 archical cross-frame constraints applied to enforce coherence in shapes, t
 extures and colors. The second part propagates the key frames to other fra
 mes with temporal-aware patch matching and frame blending. Our framework a
 chieves global style and local texture temporal consistency at a low cost 
 (without re-training or optimization). The adaptation is compatible with e
 xisting image diffusion techniques, allowing our framework to take advanta
 ge of them, such as customizing a specific subject with LoRA, and introduc
 ing extra spatial guidance with ControlNet.\nExtensive experimental result
 s demonstrate the effectiveness of our proposed framework over existing me
 thods in rendering high-quality and temporally-coherent videos.\n\nRegistr
 ation Category: Full Access, Enhanced Access, Trade Exhibitor, Experience 
 Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_345&sess=sess209
END:VEVENT
END:VCALENDAR