We present a novel motion prior, called PhaseMP, modeling a probability distribution on
pose transitions conditioned by a frequency domain feature extracted from a periodic …

We present a novel character control framework that effectively utilizes motion diffusion
probabilistic models to generate high-quality and diverse character animations, responding …

Given its wide applications, there is increasing focus on generating 3D human motions from
textual descriptions. Differing from the majority of previous works, which regard actions as …

We present C· ASE, an efficient and effective framework that learns Conditional Adversarial
Skill Embeddings for physics-based characters. C· ASE enables the physically simulated …

Recent advances in learning reusable motion priors have demonstrated their effectiveness
in generating naturalistic behaviors. In this paper, we propose a new learning framework in …

Crafting a single, versatile physics-based controller that can breathe life into interactive
characters across a wide spectrum of scenarios represents an exciting frontier in character …

Legged robots are designed to perform highly dynamic motions. However, it remains
challenging for users to retarget expressive motions onto these complex systems. In this …

In this work, we present MoConVQ, a novel unified framework for physics-based motion
control leveraging scalable discrete representations. Building upon vector quantized …

Developing controllers for physics-based character simulation and control is one of the core
challenges of computer animation. In recent years, techniques that combine deep …

Humans perform everyday tasks using a combination of locomotion and manipulation skills.
Building a system that can handle both skills is essential to creating virtual humans. We …