Interactive character animation using simulated physics: A state‐of‐the‐art review
T Geijtenbeek, N Pronost - Computer graphics forum, 2012 - Wiley Online Library
Physics simulation offers the possibility of truly responsive and realistic animation. Despite
wide adoption of physics simulation for the animation of passive phenomena, such as fluids …
wide adoption of physics simulation for the animation of passive phenomena, such as fluids …
Character controllers using motion vaes
HY Ling, F Zinno, G Cheng… - ACM Transactions on …, 2020 - dl.acm.org
A fundamental problem in computer animation is that of realizing purposeful and realistic
human movement given a sufficiently-rich set of motion capture clips. We learn data-driven …
human movement given a sufficiently-rich set of motion capture clips. We learn data-driven …
Sim-to-real learning of all common bipedal gaits via periodic reward composition
We study the problem of realizing the full spectrum of bipedal locomotion on a real robot with
sim-to-real reinforcement learning (RL). A key challenge of learning legged locomotion is …
sim-to-real reinforcement learning (RL). A key challenge of learning legged locomotion is …
Mode-adaptive neural networks for quadruped motion control
Quadruped motion includes a wide variation of gaits such as walk, pace, trot and canter, and
actions such as jumping, sitting, turning and idling. Applying existing data-driven character …
actions such as jumping, sitting, turning and idling. Applying existing data-driven character …
Auto-conditioned recurrent networks for extended complex human motion synthesis
We present a real-time method for synthesizing highly complex human motions using a
novel training regime we call the auto-conditioned Recurrent Neural Network (acRNN) …
novel training regime we call the auto-conditioned Recurrent Neural Network (acRNN) …
Phase-functioned neural networks for character control
We present a real-time character control mechanism using a novel neural network
architecture called a Phase-Functioned Neural Network. In this network structure, the …
architecture called a Phase-Functioned Neural Network. In this network structure, the …
Discovery of complex behaviors through contact-invariant optimization
We present a motion synthesis framework capable of producing a wide variety of important
human behaviors that have rarely been studied, including getting up from the ground …
human behaviors that have rarely been studied, including getting up from the ground …
Contact and human dynamics from monocular video
Existing deep models predict 2D and 3D kinematic poses from video that are approximately
accurate, but contain visible errors that violate physical constraints, such as feet penetrating …
accurate, but contain visible errors that violate physical constraints, such as feet penetrating …
FEM simulation of 3D deformable solids: a practitioner's guide to theory, discretization and model reduction
E Sifakis, J Barbic - Acm siggraph 2012 courses, 2012 - dl.acm.org
A practical guide to finite-element-method (FEM) simulation of 3D deformable solids reviews
essential offline FEM simulation techniques: complex nonlinear materials, invertible …
essential offline FEM simulation techniques: complex nonlinear materials, invertible …
Reconstructing 3d human pose from 2d image landmarks
Reconstructing an arbitrary configuration of 3D points from their projection in an image is an
ill-posed problem. When the points hold semantic meaning, such as anatomical landmarks …
ill-posed problem. When the points hold semantic meaning, such as anatomical landmarks …