3D Model Generation Method Based on Genetic Operation

Abstract

The invention relates to a three-dimensional model generation method based on genetic manipulation. The method includes the steps: inputting a three-dimensional model set; selecting optional two three-dimensional models from the three-dimensional model set and respectively marking the models as a three-dimensional model A and a three-dimensional model B; calculating corresponding values of functional parts of the three-dimensional model A and those of functional parts of the three-dimensional model B; selecting the functional parts of the three-dimensional model A and the functional parts of the three-dimensional model B, respectively marking the parts as a functional part set A10 and a functional part set B10; assembling the functional part set A10 and the functional part set B10 to obtain an assembled model; subjecting the assembled model to structural optimization to obtain a novel three-dimensional model. The method taking advantages of crisscross inheritance is simple and highly reliable, and a three-dimensional data set is enriched. In addition, a newly generated three-dimensional model can be further used as an input basic three-dimensional model which is used for next cross combination, and accordingly the three-dimensional model data set is greatly enriched.

Description

technical field [0001] The invention belongs to the field of computer graphics, in particular to a method for generating a three-dimensional model based on genetic operations. Background technique [0002] 3D modeling is one of the difficulties in the field of computer graphics. How to automatically generate a new 3D model based on the existing 3D model is an important way to solve 3D modeling and enrich the existing 3D model data set. [0003] Existing methods for automatically generating 3D models mainly include procedural modeling and structure-preserving deformation. The main disadvantage of the procedural modeling approach is the need to define the shape syntax used to generate the 3D model by the user. Shape grammar usually consists of several production rules to form a grammar system. Moreover, the structure of man-made objects is often complex, and its structure is closely related to the function of the object. Therefore, it is very difficult to define a shape gra...

AI Technical Summary

Problems solved by technology

[0005] Based on this, it is necessary to provide a 3D model generation method based on genetic manipulation to address the shortcomings of existing 3D model generation methods

Images