BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030657Z
LOCATION:Meeting Room S221\, Level 2
DTSTART;TZID=Asia/Hong_Kong:20251216T165100
DTEND;TZID=Asia/Hong_Kong:20251216T170200
UID:siggraphasia_SIGGRAPH Asia 2025_sess131_papers_1632@linklings.com
SUMMARY:Control Operators for Interactive Character Animation
DESCRIPTION:Ruiyu Gou (Epic Games), Michiel van de Panne (University of Br
 itish Columbia), and Daniel Holden (Epic Games)\n\nNeural-network-based ch
 aracter controllers are increasingly common and capable. However, the inte
 gration of desired control inputs such as joystick movement, motion paths,
  and objects in the environment, remains challenging. This is because thes
 e inputs often require custom feature engineering, specific neural network
  architectures, and training procedures. This renders these methods largel
 y inaccessible to non-technical designers. To address this challenge, we i
 ntroduce Control Operators, a powerful and flexible framework for specifyi
 ng the control mechanisms of interactive character controllers. By breakin
 g down the control problem into a set of simple operators, each with a sem
 antic meaning for designers, and a corresponding neural network structure,
  we allow non-technical users to design control mechanisms in a way that i
 s intuitive and can be composed together to train models that have multipl
 e skills and control modes. We demonstrate their potential with two curren
 t state-of-the-art interactive character controllers - a flow-matching-bas
 ed auto-regressive model, and a variation of Learned Motion Matching. We v
 alidate the approach via a user study wherein industry practitioners with 
 varying degrees of ML and technical expertise explore the use of our syste
 m.\n\nRegistration Category: Full Access, Full Access Supporter\n\nSession
  Chair: Jungdam Won (Seoul National University)\n\n
END:VEVENT
END:VCALENDAR
