BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023302Z
LOCATION:Hall C\, C Block\, Level 4
DTSTART;TZID=Asia/Tokyo:20241206T160000
DTEND;TZID=Asia/Tokyo:20241206T180000
UID:siggraphasia_SIGGRAPH Asia 2024_sess208_real_118@linklings.com
SUMMARY:Prototyping Game Character Animations with AI in Unity
DESCRIPTION:Key Events, Real-Time Live!\n\nFlorent Bocquelet, Félix Harvey
 , and Pierre-Luc Loyer (Unity Technologies)\n\nMost 3D games leverage anim
 ations to breathe life into characters. Even at the early stages of game d
 evelopment, prototyping with working animations helps developers quickly u
 nderstand and adapt the game design. Controllable characters require anima
 tions that are constrained in multiple ways in order to blend together and
  avoid artifacts such as feet sliding. Authoring, modifying and iterating 
 on such animations is a costly process that often requires high level expe
 rtise or expensive motion capture.\n\nWe present a novel AI-powered graph 
 tool that allows users to leverage generative machine learning models, pre
 sented as nodes in the graph, and create animations from only a few high-l
 evel inputs. This greatly reduces the time and expertise required to autho
 r animations from scratch, while offering unseen levels of control with ge
 nerative motion creation.\n\nThe combination of the many relevant nodes th
 at the graph supports and the flexibility of our state-of-the-art diffusio
 n models allows for going beyond text-to-motion and in-betweening, common 
 in the literature. We can generate motions that can be synchronized on mul
 tiple aspects, such as duration, speed, feet contact timings, while being 
 constrained by signals such as text-prompts and trajectories. Our diffusio
 n models also allow for stylizing existing motions, and generating looping
  animations. This makes it possible, for the first time to our knowledge, 
 to generate complete working locomotion sets from high level inputs such a
 s text and duration, directly usable with common character controllers.\n\
 nOur system being implemented in Unity, we showcase the power of this nove
 l approach by constructing a prototype animated character with working loc
 omotion and attack motions without pre-existing animations, in a few minut
 es.\n\nRegistration Category: Enhanced Access, Full Access, Full Access Su
 pporter\n\nLanguage Format: English Language\n\nSession Chair: Takahito Te
 jima (Polyphony Digital Inc.)
URL:https://asia.siggraph.org/2024/program/?id=real_118&sess=sess208
END:VEVENT
END:VCALENDAR