Grant: Alliance Grants
Simon Fraser University
$75,000.00
Human Motion Synthesis For Character Animation
FY 2024-25
Summary
Animation systems that can synthesize life-like and responsive behaviors for virtual characters are a crucial component towards building immersive and interactive virtual worlds. However, modern animation workflows remain highly manual and labour intensive. These methods tend to produce stiff and unresponsive animations that lead to unrealistic behaviors, especially for interaction applications. This research proposal outlines a plan for leveraging physics-based simulation and machine learning to develop virtual characters that can perform more life-like and intelligent behaviors in complex environments.
In this proposed research program, the applicant and Electronic Arts will advance the capabilities of simulated characters by 1) developing techniques for simulating life-like interactions with realistic indoor and outdoor environments, 2) create methods for synthesizing interactions between large groups of characters, 3) construct reusable motion control models that enable characters to quickly learn new behaviors, and 4) develop methods for evaluating the realism of behaviors produced by virtual characters.
Canada is a globally recognized hub for animation, video games, and visual effects. The proposed research program can create powerful new tools for animating virtual characters. These techniques offer the potential to drastically lower the cost of animating virtual characters, enable novel user experiences, and open new possibilities for storytelling and artistic expression in the field of animation.
Program
Alliance Grants
Recipient
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
597717-2024
Name nom
Peng, Xue Bin XB
Department département
Computing Science, School of
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
75000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2707
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Graphics
Research subject fr
Infographie
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Human Motion Synthesis For Character Animation
Keywords
animation; computer graphics; generative models; machine learning; reinforcement learning
Application summary
Animation systems that can synthesize life-like and responsive behaviors for virtual characters are a crucial component towards building immersive and interactive virtual worlds. However, modern animation workflows remain highly manual and labour intensive. These methods tend to produce stiff and unresponsive animations that lead to unrealistic behaviors, especially for interaction applications. This research proposal outlines a plan for leveraging physics-based simulation and machine learning to develop virtual characters that can perform more life-like and intelligent behaviors in complex environments.
In this proposed research program, the applicant and Electronic Arts will advance the capabilities of simulated characters by 1) developing techniques for simulating life-like interactions with realistic indoor and outdoor environments, 2) create methods for synthesizing interactions between large groups of characters, 3) construct reusable motion control models that enable characters to quickly learn new behaviors, and 4) develop methods for evaluating the realism of behaviors produced by virtual characters.
Canada is a globally recognized hub for animation, video games, and visual effects. The proposed research program can create powerful new tools for animating virtual characters. These techniques offer the potential to drastically lower the cost of animating virtual characters, enable novel user experiences, and open new possibilities for storytelling and artistic expression in the field of animation.