Three-dimensional shape and texture reconstruction method and system based on single image and storage medium

Abstract

The invention relates to a three-dimensional shape and texture reconstruction method and system based on a single image and a storage medium, and solves the problem that three-dimensional face data cannot be efficiently and accurately obtained. The method comprises the following steps: acquiring face image information; analyzing the face image information through a normalized coordinate coding prediction network, and mapping the analyzed data information to a UV space to form UV space texture mapping information; analyzing the UV spatial texture mapping information through a filling network toobtain complete texture map information; analyzing the complete texture map information through a shape network to obtain UV position map information; searching face three-dimensional shape coordinate information corresponding to the current UV position map information from a preset corresponding relationship between reference UV position map information and reference face three-dimensional shapecoordinate information; and forming three-dimensional texture face information according to the searched face three-dimensional shape coordinate information. According to the invention, the requiredreconstructed three-dimensional face data can be efficiently and accurately obtained.

Description

technical field [0001] The present invention relates to the technical field of three-dimensional reconstruction, in particular to a single-image-based three-dimensional shape and texture reconstruction method, system and storage medium. Background technique [0002] 3D face reconstruction based on 2D images is a technology with a wide range of application scenarios. It can be used in face animation generation, human-computer interaction, and medical beauty industry. The general implementation method includes the following two technical solutions: [0003] 1) The method based on the 3D deformation model: the method based on the 3D deformation model uses statistical methods to extract the average face from the actual 3D face in the laboratory scene (respectively shape average face and texture average face ) and face coefficients (shape coefficient and texture coefficient). Then, iteratively optimizes the two-dimensional face by using constraints such as key points of the fac...

AI Technical Summary

Problems solved by technology

[0007] Although the reconstructed face data can be obtained through the above-mentioned 3D face reconstruction method and texture restoration method, the method based on the 3D deformation model or the method of restoring the 3D model from the shadow, or the overall efficiency is low and the accuracy rate is low. , or the requirements for initializing the 3D face are high, so the required reconstruction face data cannot be obtained efficiently and accurately, so there is a certain room for improvement

Images