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:20240214T070246Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T091500
DTEND;TZID=Australia/Melbourne:20231214T093000
UID:siggraphasia_SIGGRAPH Asia 2023_sess165_papers_427@linklings.com
SUMMARY:Controllable Group Choreography using Contrastive Diffusion
DESCRIPTION:Technical Papers, TOG\n\nNhat Le and Tuong Do (AIOZ); Khoa Do 
 (VNUHCM-University of Science); Hien Nguyen, Erman Tjiputra, and Quang Tra
 n (AIOZ); and Anh Nguyen (University of Liverpool)\n\nMusic-driven group c
 horeography poses a considerable challenge but holds significant potential
  for a wide range of industrial applications. The ability to generate sync
 hronized and visually appealing group dance motions that are aligned with 
 music opens up opportunities in many fields such as entertainment, adverti
 sing, and virtual performances. However, most of the recent works are not 
 able to generate high-fidelity long-term motions, or fail to enable contro
 llable experience. In this work, we aim to address the demand for high-qua
 lity and customizable group dance generation by effectively governing the 
 consistency and diversity of group choreographies. In particular, we utili
 ze a diffusion-based generative approach to enable the synthesis of flexib
 le dancers and long-term group dances, while ensuring coherence to the inp
 ut music. Ultimately, we introduce a Group Contrastive Diffusion (GCD) str
 ategy to enhance the connection between dancers and their group, presentin
 g the ability to control the consistency or diversity level of the synthes
 ized group animation via the classifier-guidance sampling technique. Throu
 gh intensive experiments and evaluation, we demonstrate the effectiveness 
 of our approach in producing visually captivating and consistent group dan
 ce motions. The experimental results show the capability of our method to 
 achieve the desired levels of consistency and diversity, while maintaining
  the overall quality of the generated group choreography.\n\nRegistration 
 Category: Full Access
URL:https://asia.siggraph.org/2023/full-program?id=papers_427&sess=sess165
END:VEVENT
END:VCALENDAR