Translating motions from a real user onto a virtual embodied avatar is a key challenge for
character animation in the metaverse. In this work, we present a novel generative framework …

We propose Selfrionette, a controller that uses fingertip force input to drive avatar
movements in virtual reality (VR). This system enables users to interact with virtual objects …

Our goal is to simulate how humans recover balance after external perturbation, eg, being
pushed. While different strategies can be adopted to achieve balance recovery, we …

In the character animation field, modern supervised keyframe interpolation models have
demonstrated exceptional performance in constructing natural human motions from sparse …

Many VR animal embodiment sytsems suffer from poor animation fidelity, typically animating
the animal avatars using inverse kinematics. We address this issue, presenting a novel deep …

Creating plausible motions for a diverse range of characters is a long‐standing goal in
computer graphics. Current learning‐based motion synthesis methods rely on large‐scale …

Humanoid robots are increasingly being developed for seamless interaction with humans in
various domains. However, generating expressive and feasible motions for these robots …

Motion retargeting is a technique for applying the motion of one character to a new
character. Differences in shapes and proportions between characters can cause self …

This paper presents a method for retargeting motion onto a character with a completely
different skeleton and mesh. We simplify the source and target meshes into a short list of …