Invention Grant
- Patent Title: Machine learning acceleration of complex deformations such as muscle, skin and clothing simulation
-
Application No.: US17676087Application Date: 2022-02-18
-
Publication No.: US11887233B2Publication Date: 2024-01-30
- Inventor: David Sebastian Minor
- Applicant: David Sebastian Minor
- Applicant Address: CA Vancouver
- Assignee: Digital Domain Virtual Human (US), Inc.
- Current Assignee: Digital Domain Virtual Human (US), Inc.
- Current Assignee Address: US CA Los Angeles
- Agency: Oyen Wiggs Green & Mutala LLP
- Agent Todd A. Rattray
- Main IPC: G06T13/40
- IPC: G06T13/40 ; G06T19/00 ; G06N3/08 ; G06T17/20

Abstract:
Methods and systems are provided preparing training data for training a neural network to simulate deformations of a surface of a CG character, for training a neural network to simulate deformations of a surface of a CG character and for employing a neural network to simulate deformations of a surface of a CG character. Matrix decomposition techniques are used to generate the training data and are subsequently used by trained neural networks during inference to reconstruct CG character surfaces. The inference methods and systems are suitable for real time animation applications.
Public/Granted literature
- US20230267666A1 MACHINE LEARNING ACCELERATION OF COMPLEX DEFORMATIONS SUCH AS MUSCLE, SKIN AND CLOTHING SIMULATION Public/Granted day:2023-08-24
Information query