Method and system for realizing three-dimensional facial expression and mouth shape by synchronously driving text

Abstract

The invention discloses a text synchronous driving three-dimensional facial expression and mouth shape realization method and system, and the method comprises the following steps: a preprocessing stage: S1, making a B l endshape change curve: making a curve in Maya; the curves comprise two types of mouth shape and expression starting and ending change curves; the mouth shape change curve comprises mouth shape curve groups of all counted adjacent phoneme sequence pairs, and for specific expressions, the mouth shape change curve comprises two change curves from neutral change to specific expression, namely expression start and from specific expression change to immediate expression end; s2, manufacturing a B < l > endshape: in the Maya, manufacturing the B < l > endshape; the mouth shape B l endshape comprises three groups of mouth shapes of immobile mouth corners, upward mouth corners and laugh mouth corners, each group comprises six mouth shapes of Fv, Open, PBM, ShCh, W and wi de, and the expression B l endshape is made. According to the method, the natural and vivid mouth shape and expression animation can be synchronously driven through the text, meanwhile, the mouth corner part can be naturally fused, and the intelligent interaction capability of the virtual human is improved.

Description

technical field [0001] The invention relates to the technical field of computer software, in particular to a method and system for realizing text synchronous driving of three-dimensional facial expressions and mouth shapes. Background technique [0002] Digital virtual humans have gradually landed in the fields of virtual idols, virtual anchors, virtual consultants, etc., especially in the recently very popular metaverse, as the virtual avatar of human beings in the virtual world, the digital virtual human with lifelike and intelligent interaction ability is extremely crucial part. Intelligent interaction capabilities include many aspects. From the perspective of behavioral performance, multimodal behaviors such as mouth shapes, expressions, and non-verbal behaviors are required. At present, there are two categories of speech-driven behavior and text-driven behavior. The voice driver is relatively mature, while the text driver is relatively difficult to handle because the ...

AI Technical Summary

Problems solved by technology

Because expression changes usually include changes in the corners of the mouth, and changes in mouth shapes also include changes in the corners of the mouth. When mouth shapes and expressions change synchronously, it is difficult to properly integrate the common parts, resulting in unnatural mouth expression animations.

Images