3D Facial Expression Generation via Skeleton Binding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for processing facial expressions on virtual objects are time-consuming and inefficient, particularly when aiming for specific styles like cartoon or anime, as they require manual art design.
Innovation Solution
A facial expression processing method that determines a skeletal structure of a three-dimensional facial model, binds action units in a style expression template to corresponding bones, and drives bone movement based on expression controls to generate expressions conforming to the target style, using a computer device and storage medium.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual art design is used to process facial expressions on virtual objects, then the expressions can conform to specific styles (cartoon, anime, etc.), but the process consumes a lot of time and results in low efficiency
Solution Approach 1:
The patent replaces the manual mechanical design process with an automated computer-based system. The system uses skeletal structure determination, skinning technology, and action unit binding to automatically generate style-conformant facial expressions, substituting human art designers with computational algorithms that can rapidly produce styled expressions without manual intervention
Solution Approach 2:
The patent transforms the expression generation process by changing parameters from manual artistic control to automated parameter-driven control. By defining action units, binding them to skeletal bones, and using expression controls with adjustable parameters, the system can rapidly generate different expressions by modifying numerical parameters rather than manual design, maintaining style conformity while dramatically improving efficiency
2Manufacturing precision
If manual processing is used for each facial expression, then high quality styled expressions can be achieved, but the time consumption increases significantly
Solution Approach 1:
The patent implements preliminary action by pre-defining action units and their corresponding bone bindings before actual expression generation. The skeletal structure and skinning are established in advance, creating a reusable framework that allows rapid generation of multiple expressions without repeating the entire design process, thus reducing time consumption while maintaining quality
Solution Approach 2:
The patent uses copying by creating reusable action unit templates that can be applied to generate multiple expressions. Once an action unit is defined and bound to bones, it can be copied and reused for different expressions by adjusting parameters, eliminating the need to manually design each expression from scratch while preserving the styled quality
Data Source
AI summary
This application relates to a facial expression processing method performed by a computer device, the method including: determining a skeletal structure of a three-dimensional facial model of a target style; skinning the skeletal structure to generate a virtual object face; binding an action unit in a style expression template matching the target style to a one or more corresponding bones in the skeletal structure; associating at least one expression control with at least one action unit in the style expression template; in response to an adjustment operation on the at least one expression control, driving bones bound to the at least one action unit to move based on information of the at least one action unit associated with the expression control; and controlling the virtual object face to generate an expression conforming to the target style in accordance with the movement of the bones triggered by the adjustment operation.