Multi-modal infinite expression synthesis method and device based on virtual digital human
An expression synthesis and multi-modal technology, applied in character and pattern recognition, image data processing, still image data retrieval, etc., can solve problems such as difficult application of generalized scenes, complex processing process of expression processing technology, etc., to simplify expression productivity , increase the interactive experience, the effect of anthropomorphic real emotion
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0034] see figure 1 and figure 2 , providing a multi-modal infinite expression synthesis method based on a virtual digital human, comprising the following steps:
[0035] S1. Obtain basic expression material, and convert the basic expression material into an expression digital model for storage;
[0036] S2. Classifying the expression digital models to obtain a classified expression model library; the classified expression model library includes a micro-expression library, a macro-expression library and a mouth-shaped library, and stores the basic expression material through the classified expression model library identity tag;
[0037] S3. Using the identity tag, select an expression digital model to be synthesized from the classified expression model library, and generate the selected expression digital model into a synthesized expression.
[0038] see image 3 , in this embodiment, the method of acquiring the basic expression material includes: collecting or scanning t...
Embodiment 2
[0054] see Figure 5 , the present invention also provides a multi-modal infinite expression synthesis device based on a virtual digital human, including:
[0055] The expression material acquisition module 1 is used to obtain the basic expression material, and converts the basic expression material into an expression digital model for storage;
[0056] Expression model classification module 2, is used for classifying described expression digital model, obtains classification expression model storehouse; Described classification expression model storehouse comprises micro-expression storehouse, macro expression storehouse and mouth shape storehouse, stores by described classification expression model storehouse The identity tag of the basic expression material;
[0057] Synthetic expression generation module 3 is used for using said identity tag to select an expression digital model to be synthesized from said classified expression model library, and generate the selected exp...
Embodiment 3
[0066] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, the computer-readable storage medium stores program codes for a multi-modal infinite expression synthesis method based on a virtual digital human, and the program codes include: Execute the instructions of the virtual digital human-based multi-modal infinite expression synthesis method in Embodiment 1 or any possible implementation thereof.
[0067] The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server, a data center, etc. integrated with one or more available media. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, or a magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, a solid state disk (SolidState Disk, SSD)).
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More