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:20240214T070249Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T102500
DTEND;TZID=Australia/Melbourne:20231215T104000
UID:siggraphasia_SIGGRAPH Asia 2023_sess135_papers_248@linklings.com
SUMMARY:Text-Guided Synthesis of Eulerian Cinemagraphs
DESCRIPTION:Technical Papers, TOG\n\nAniruddha Mahapatra (Carnegie Mellon 
 University); Aliaksandr Siarohin, Hsin-Ying Lee, and Sergey Tulyakov (Snap
  Inc.); and Jun-Yan Zhu (Carnegie Mellon University)\n\nWe introduce Text2
 Cinemagraph,  a fully automated method for creating cinemagraphs from text
  descriptions - an especially challenging task when prompts feature imagin
 ary elements and artistic styles, given the complexity of interpreting the
  semantics and motions of these images. We focus on cinemagraphs of fluid 
 elements, such as flowing rivers, and drifting clouds, which exhibit conti
 nuous motion and repetitive textures. Existing single-image animation meth
 ods fall short on artistic inputs, and recent text-based video methods fre
 quently introduce temporal inconsistencies, struggling to keep certain reg
 ions static. To address these challenges, we propose an idea of synthesizi
 ng image 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 re
 alistic counterpart greatly simplifies layout and motion analysis.  Levera
 ging existing natural image and video datasets, we can accurately segment 
 the realistic image and predict plausible motion given the semantic inform
 ation. The predicted motion can then be transferred to the artistic image 
 to create the final cinemagraph. Our method outperforms existing approache
 s in creating cinemagraphs for natural landscapes as well as artistic and 
 other-worldly scenes, as validated by automated metrics and user studies. 
 Finally, we demonstrate two extensions: animating existing paintings and c
 ontrolling motion directions using text.\n\nRegistration Category: Full Ac
 cess\n\nSession Chair: Chongyang Ma (ByteDance)
URL:https://asia.siggraph.org/2023/full-program?id=papers_248&sess=sess135
END:VEVENT
END:VCALENDAR