Texture and normal library construction method and texture and normal graph generation method and device

Abstract

The invention discloses a texture and normal library construction method based on an artificial intelligence technology. The texture and normal library construction method comprises the steps of obtaining a first original face texture map set; generating a first sampling face texture map set according to the first original face texture map set; for the target face area, determining a first principal component analysis parameter according to the first sampling face texture map set; for the target face area, if the face texture and normal library construction conditions are met, using the firstprincipal component analysis parameter as a texture normal base corresponding to the target face area in the face texture and normal library, wherein the face texture and normal library further comprises (K1) a texture normal base corresponding to the face area. The embodiment of the invention further provides a texture and normal graph generation method and device, a new human face texture and normal library can be constructed, the human face texture graph with low definition can be restored into the ultrahigh-definition human face texture graph by using the human face texture and normal library, and expression of the human face texture graph is enhanced.

Description

technical field [0001] The present application relates to the field of computer vision, in particular to a method for constructing a texture and normal library, a method and a device for generating a texture and normal map. Background technique [0002] With the development of deep learning, 3D face has played an increasingly important role in many fields. Generating 3D face models is a powerful tool in computer vision (CV), and these 3D face models achieve pose and illumination invariance by modeling the 3D face space and imaging process. [0003] The existing open source face texture library includes Dynamic 3DFacial Action Coding System Dataset (D3DFacs). When constructing D3DFACS, a series of faces are scanned by high-precision scanning equipment or low-precision scanning equipment. and its corresponding texture information. [0004] However, the texture maps in the face texture library usually have a small size. For example, the size of the face texture map provided i...

AI Technical Summary

Problems solved by technology

[0004] However, the texture maps in the face texture library usually have a small size. For example, the size of the face texture map provided in D3DFACS is 1024×1280, and a small texture map means that there are defects in texture expression, which is difficult to Complete the task of fitting ultra-high-definition face images

Images