Triangular mesh model generation method and device

Abstract

The invention discloses a triangular mesh model generation method and device, and the method comprises the steps: processing an original image, and obtaining contour data; calculating a density value,and processing the contour data according to the density value to obtain a contour point set; processing an internal region of a contour formed by the contour point set according to the sparse density value to obtain a contour internal point set; and obtaining triangular mesh model data by using the contour point set and the contour internal point set to complete the generation of a triangular mesh model. The method has the technical effects that the uniform triangular mesh model can be automatically generated, and the problems of unnatural stretching effect and the like generated in the picture processing process are effectively avoided.

Description

technical field [0001] The present application relates to the technical field of computer graphics, in particular to a method and device for generating a triangular mesh model. Background technique [0002] At present, in virtual fitting products, after taking photos of various clothes and accessories to generate pictures, it is necessary to transform the clothes pictures and then attach them to the models to achieve the effect of trying on clothes. To achieve this goal, manual adjustment is usually used, that is, image processing software is used to manually modify and deform the picture, but the efficiency of manual operation is too low, the effect is difficult to guarantee, and the requirements of automatic processing cannot be met. And the existing methods of automatically stretching and deforming pictures by algorithms such as affine transformation and linear transformation are difficult to achieve the purpose of fitting. However, when clothing pictures are covered wit...

AI Technical Summary

Problems solved by technology

To achieve this goal, manual adjustment is usually used, that is, manual image processing software is used to modify and deform the picture, but the efficiency of manual operation is too low, the effect is difficult to guarantee, and the requirements of automatic processing cannot be met.

Moreover, the existing methods of automatically stretching and deforming pictures through algorithms such as affine transformation and linear transformation are difficult to achieve the purpose of fitting

However, when clothing pictures are covered with triangular meshes, due to the influence of the curvature of the contour curve, the commonly used methods of generating triangular meshes to cover clothing pictures will have uneven density, which eventually leads to failure when stretching the triangle vertices. Produces a natural, even stretch effect on areas of clothing within the contour

Images