Face texture image acquisition method and device, equipment and storage medium

Abstract

The invention provides a face texture image acquisition method and device, equipment and a storage medium. The method comprises the steps that point cloud of a three-dimensional face model of a targetobject and face images of n head postures of the target object are acquired; index information of three-dimensional data points in the point cloud is calculated through cylindrical expansion; obtaining a mapping relationship between three-dimensional data points in the point cloud and pixel points on the face image; image areas corresponding to the head postures are obtained from the n face images respectively, and n effective areas are obtained; generating region texture images corresponding to the n effective regions according to the index information and the mapping relationship; and performing image fusion on the n region texture images to generate a face texture image of the target object. According to the method, the corresponding face texture image can be generated for the three-dimensional face model obtained through arbitrary reconstruction, so that the texture rendering effect of the three-dimensional face model can be improved, and the authenticity of the finally generatedface texture image can be improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of computer vision of artificial intelligence, and in particular to a method, device, device and storage medium for acquiring a face texture image. Background technique [0002] 3D (3Dimensions, three-dimensional) face reconstruction refers to reconstructing a 3D model of a human face from one or more 2D (2Dimensions, two-dimensional) images. [0003] In some related technologies, one or more face images of the target object are obtained by shooting, and these face images are analyzed and processed to generate a point cloud of the 3D face model of the target object; then, for the point cloud For each point, find the pixel point corresponding to the point from the face image, and use the color of the pixel point as the color of this point. The color of each triangular face on the 3D face model is determined by the average color of the three points that make up the triangular face....

AI Technical Summary

Problems solved by technology

[0004] However, the textured 3D face model generated by rendering with the above-mentioned related technologies has a large color change in each area and the effect is rough.

Images