Cmlabs Simulations Inc.

Disney Enterprises, Inc.

Sheldon Paul Andrews

Paul Gregory Kry

Marek Teichmann

Leonid Sigal

Kenneth John Mitchell

Jozsef Kovecses

Albert Peiret Gimenez

Ivan Huerta Casado

Methods and systems for executing a simulation of a multibody system are described herein. In one broad aspect, there is provided a computer-implemented method for executing a simulation of a multibody system, where a physics-based simulator is used to simulate the multibody system by: partitioning the multibody system into a plurality of subsystems, the multibody system comprising bilateral and unilateral constraints, and a set of interfaces that couple at least two of the subsystems is defined; at each of a plurality of time steps, employing a Schur complement method to compute an effective mass at each interface of the set of interfaces, and solving each of the plurality of subsystems to obtain a plurality of internal impulses.

Systems and methods for simulating multibody systems

Training data from multiple types of sensors and captured in previous capture sessions can be fused within a physics-based tracking framework to train motion priors using different deep learning techniques, such as convolutional neural networks (CNN) and Recurrent Temporal Restricted Boltzmann Machines (RTRBMs). In embodiments employing one or more CNNs, two streams of filters can be used. In those embodiments, one stream of the filters can be used to learn the temporal information and the other stream of the filters can be used to learn spatial information. In embodiments employing one or more RTRBMs, all visible nodes of the RTRBMs can be clamped with values obtained from the training data or data synthesized from the training data. In cases where sensor data is unavailable, the input nodes may be unclamped and the one or more RTRBMs can generate the missing sensor data.

Deep-learning motion priors for full-body performance capture in real-time

Methods of and systems for executing a simulation of a constrained multi-body system. The method comprises, using a physics engine, simulating the constrained multi-body system, wherein: the constrained multi-body system comprises articulated constraints, the articulated constraints are associated with a geometric stiffness matrix; the geometric stiffness matrix defining a geometric stiffness; a diagonal approximation of the geometric stiffness matrix is generated; and the diagonal approximation is used as part of a stability analysis in which damping is automatically adjusted so that the damping stabilizes the simulation of the constrained multi-body system.

System and method for executing a simulation of a constrained multi-body system

Growing community of inventors

Ottawa, Canada

Sheldon Paul Andrews