Modeling method of nonlinear three-dimensional face

Abstract

The invention relates to a modeling method of a nonlinear three-dimensional face, which has better reconstruction effect, and comprises the following steps: (1) respectively selecting three-dimensional samples and two-dimensional samples from the exiting face database as training sample sets and carrying out the standardized operation on the samples; pairing the two-dimensional training sample set and the three-dimensional training sample set during the training stage according to the identity information, so that the samples in the two groups of sample sets mutually correspond according to the identity information; (2) training respective projection matrixes based on the two groups of sample sets, so that samples with different dimensionalities have maximum relevance after being projected; (3) during the reconstruction stage, carrying out standardized treatment on an inputted two-dimensional face image, projecting in a subspace of the two-dimensional training sample set, selecting three-dimensional samples with high relevance according to the relevance distance, constructing a three-dimensional face model based on the selected three-dimensional samples and matching the three-dimensional face model with the inputted image to realize the reconstruction of a three-dimensional face sample.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a nonlinear three-dimensional human face modeling method. Background technique [0002] 3D face reconstruction is the work of reconstructing its 3D face data from an input 2D face image. Since the 3D face model has broad application prospects in computer games, human-computer interaction and other fields, 3D face reconstruction has become the most active research hotspot in computer graphics and computer vision. Face modeling has received extensive attention since Parke first used computer methods to represent faces in 1972. After more than 30 years of development, 3D face modeling methods have made great progress. Vetter et al. proposed a face modeling method based on a deformable model in 1999. This method was the first to experiment with the complete automation of face modeling, and can reconstruct a specific person's 3D face model from a face image. Si...

AI Technical Summary

Problems solved by technology

The reconstruction algorithm based on linear theory will inevitably ignore the details of the face structure, and it is difficult to achieve a good reconstruction effect

Images