119 citations · 129 across the 6 of their papers we have counts for
9 papers · 1 filter
InstantMimic: A High Performance System for Learning Physics-based Skills in Seconds
Ikjun Choi, Geonho Leem, Jungdam Won
Physics-based character control is a long-standing challenge in computer graphics and robotics, requiring policies that satisfy complex dynamics while producing realistic motion. R…
Versatile Physics-based Character Control with Hybrid Latent Representation
Jinseok Bae, Jungdam Won, Donggeun Lim +2
We present a versatile latent representation that enables physically simulated character to efficiently utilize motion priors. To build a powerful motion embedding that is shared a…
Strategy and Skill Learning for Physics-based Table Tennis Animation
Jiashun Wang, Jessica Hodgins, Jungdam Won
Recent advancements in physics-based character animation leverage deep learning to generate agile and natural motion, enabling characters to execute movements such as backflips, bo…
MOCHA: Real-Time Motion Characterization via Context Matching
Deok-Kyeong Jang, Yuting Ye, Jungdam Won +1
Transforming neutral, characterless input motions to embody the distinct style of a notable character in real time is highly compelling for character animation. This paper introduc…
DROP: Dynamics Responses from Human Motion Prior and Projective Dynamics
Yifeng Jiang, Jungdam Won, Yuting Ye +1
Synthesizing realistic human movements, dynamically responsive to the environment, is a long-standing objective in character animation, with applications in computer vision, sports…
QuestEnvSim: Environment-Aware Simulated Motion Tracking from Sparse Sensors
Sunmin Lee, Sebastian Starke, Yuting Ye +2
Replicating a user's pose from only wearable sensors is important for many AR/VR applications. Most existing methods for motion tracking avoid environment interaction apart from fo…