Human face expression animation generation method

Abstract

The invention relates to three-dimensional (3D) image processing, in particular to rapid human face expression animation generation technique based on movement capture data, and discloses a human face expression animation generation method. The human face expression animation generation method includes the following steps: one, movement capture of facial expression of a performer; two, generation of a human face texture image of a facial image; three, human face deformation by using of a radial basis function; four, personalized human face model area division; five, personalized human face model subarea deformation and integration; and six, human face animation generation. The human face expression animation generation method effectively overcomes the shortcomings that manufacturing of 3D human face animation is high in cost, low in fidelity, tedious in operation and low in efficiency in the prior art.

Description

technical field [0001] The technical scheme of the present invention relates to the processing of three-dimensional (3D) images, in particular to a method for generating animations of human facial expressions. Background technique [0002] At present, some 3D face modeling technologies can be found, such as laser scanning, stereoscopic camera, etc., which are all based on computer vision methods. These methods are expensive, difficult to popularize, and require high-intensity calculations. Commonly used standard face models for 3D face modeling and animation can be produced and exported by software such as Poser, Maya, and 3D Max, but manual adjustments are often required, which is cumbersome, time-consuming, and inefficient. [0003] CN1383102A discloses a method for making a three-dimensional human face animation. First, obtain a three-dimensional human face grid model, then divide the model into functional areas, and design motion control according to the motion character...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a facial expression animation generation method, which is a fast facial expression animation generation technology based on motion capture data, using a camera to capture a frontal photo of a person's face as a texture map, and using the radial basis function ( That is, RBF) technology deforms the standard face model, remaps the texture to generate a personalized face, then divides the personalized face model into different parts, and then deforms each partition separately, and constructs the final face model through fusion. Then generate facial expression animation, which effectively overcomes the shortcomings of high production cost, low fidelity, cumbersome operation and low efficiency of 3D facial animation in the prior art

Images