Individualized realistic virtual character modeling method based on images

Abstract

The invention provides an individualized realistic virtual character modeling method based on images. Four human body images on the facade, lateral surfaces and back quickly generate an individualized three-dimensional human body model with realistic appearance. The method comprises the following steps: using a human body model based on a swept surface as a human body template model; extracting human body characteristic information from the images, establishing a corresponding relation between the human body template model and the human body images, and deforming the human body template model to generate an individualized human body geometric model; and on the two-dimensional parameterized results of the human body model, generating vivid human body textures by the human body images, and seamlessly mapping the human body textures to the three-dimensional individualized human body model to obtain the individualized human body model with realistic visual effect. The human body images are from a camera, a video camera and the like. The method provides a new low-cost and efficient human body modeling path for the field of virtual reality and digital entertainment.

Description

technical field [0001] The invention belongs to the fields of computer graphics and image processing technology, virtual reality and digital entertainment, and relates to a method for generating a personalized human body model with realistic visual appearance by using four human body images captured from the front, side and back. Background technique [0002] At present, 3D human body modeling is mostly realized through the following three methods: the method of interactive geometric modeling, the method of 3D reconstruction and the method based on samples. [0003] The method of interactive geometric modeling is mostly completed by manual interaction with the help of 3D modeling software such as Maya according to the anatomical structure and shape characteristics of the human body. Usually, professional artists are required to be competent for modeling work, which takes a long time and costs a lot. [0004] The reconstruction method can obtain a fine geometric model throug...

AI Technical Summary

Problems solved by technology

This method based on vertex-by-vertex deformation usually lacks semantic information of the human body, resulting in inefficient deformation process of the model, and at the same time, the deformation process is prone to model self-intersection, etc.; while mapping texture through cylindrical projection, the human body needs to be divided into torso And the 5 regions of the limbs are texture mapped separately, which is easy to cause texture deformation and texture cracks on the border of adjacent regions, which affects the visual effect

Images