Deepphase: Periodic autoencoders for learning motion phase manifolds
Learning the spatial-temporal structure of body movements is a fundamental problem for
character motion synthesis. In this work, we propose a novel neural network architecture …
character motion synthesis. In this work, we propose a novel neural network architecture …
Questsim: Human motion tracking from sparse sensors with simulated avatars
Real-time tracking of human body motion is crucial for interactive and immersive
experiences in AR/VR. However, very limited sensor data about the body is available from …
experiences in AR/VR. However, very limited sensor data about the body is available from …
Physics-based character controllers using conditional vaes
High-quality motion capture datasets are now publicly available, and researchers have used
them to create kinematics-based controllers that can generate plausible and diverse human …
them to create kinematics-based controllers that can generate plausible and diverse human …
Controlvae: Model-based learning of generative controllers for physics-based characters
In this paper, we introduce ControlVAE, a novel model-based framework for learning
generative motion control policies based on variational autoencoders (VAE). Our framework …
generative motion control policies based on variational autoencoders (VAE). Our framework …
Learning and adapting agile locomotion skills by transferring experience
Legged robots have enormous potential in their range of capabilities, from navigating
unstructured terrains to high-speed running. However, designing robust controllers for highly …
unstructured terrains to high-speed running. However, designing robust controllers for highly …
Perpetual humanoid control for real-time simulated avatars
We present a physics-based humanoid controller that achieves high-fidelity motion imitation
and fault-tolerant behavior in the presence of noisy input (eg pose estimates from video or …
and fault-tolerant behavior in the presence of noisy input (eg pose estimates from video or …
Moconvq: Unified physics-based motion control via scalable discrete representations
H Yao, Z Song, Y Zhou, T Ao, B Chen… - ACM Transactions on …, 2024 - dl.acm.org
In this work, we present MoConVQ, a novel unified framework for physics-based motion
control leveraging scalable discrete representations. Building upon vector quantized …
control leveraging scalable discrete representations. Building upon vector quantized …
C· ase: Learning conditional adversarial skill embeddings for physics-based characters
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 …
Skill Embeddings for physics-based characters. C· ASE enables the physically simulated …
Physics-based character animation and human motor control
J Llobera, C Charbonnier - Physics of Life Reviews, 2023 - Elsevier
Motor neuroscience and physics-based character animation (PBCA) approach human and
humanoid control from different perspectives. The primary goal of PBCA is to control the …
humanoid control from different perspectives. The primary goal of PBCA is to control the …
Neural categorical priors for physics-based character control
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 …
in generating naturalistic behaviors. In this paper, we propose a new learning framework in …