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:20240214T070242Z
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_248@linklings.com
SUMMARY:Text-Guided Synthesis of Eulerian Cinemagraphs
DESCRIPTION:Technical Papers\n\nAniruddha Mahapatra (Carnegie Mellon Unive
 rsity); Aliaksandr Siarohin, Hsin-Ying Lee, and Sergey Tulyakov (Snap Inc.
 ); and Jun-Yan Zhu (Carnegie Mellon University)\n\nWe introduce Text2Cinem
 agraph,  a fully automated method for creating cinemagraphs from text desc
 riptions - an especially challenging task when prompts feature imaginary e
 lements and artistic styles, given the complexity of interpreting the sema
 ntics and motions of these images. We focus on cinemagraphs of fluid eleme
 nts, such as flowing rivers, and drifting clouds, which exhibit continuous
  motion and repetitive textures. Existing single-image animation methods f
 all short on artistic inputs, and recent text-based video methods frequent
 ly introduce temporal inconsistencies, struggling to keep certain regions 
 static. To address these challenges, we propose an idea of synthesizing im
 age twins from a single text prompt - a pair of an artistic image and its 
 pixel-aligned corresponding natural-looking twin. While the artistic image
  depicts the style and appearance detailed in our text prompt, the realist
 ic counterpart greatly simplifies layout and motion analysis.  Leveraging 
 existing natural image and video datasets, we can accurately segment the r
 ealistic image and predict plausible motion given the semantic information
 . The predicted motion can then be transferred to the artistic image to cr
 eate the final cinemagraph. Our method outperforms existing approaches in 
 creating cinemagraphs for natural landscapes as well as artistic and other
 -worldly scenes, as validated by automated metrics and user studies. Final
 ly, we demonstrate two extensions: animating existing paintings and contro
 lling motion directions using text.\n\nRegistration Category: Full Access,
  Enhanced Access, Trade Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_248&sess=sess209
END:VEVENT
END:VCALENDAR