Internet image driven automatic selection method of optimal view of three-dimensional model

An Internet image and 3D model technology, which is applied in the field of automatic selection of optimal views of 3D models driven by Internet images, can solve problems such as poor results and large computational overhead, achieve high attitude consistency, achieve repeatability, high The effect of calculating speed

Active Publication Date: 2014-12-03
NANJING UNIV
View PDF5 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Document 6: Chinese invention patent, CN102163343, method for automatically obtaining the best viewing angle of a 3D model based on Internet images, using this definition to obtain the optimal view of a 3D model, but only using some simple feature

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Internet image driven automatic selection method of optimal view of three-dimensional model
  • Internet image driven automatic selection method of optimal view of three-dimensional model
  • Internet image driven automatic selection method of optimal view of three-dimensional model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0103] In this embodiment, a set of 3D models is input, and the optimal view of each 3D model can be obtained through the method for automatically selecting an optimal view of a 3D model according to the present invention. Taking an unmarked car model as an example, its three views are as follows figure 2 As shown, the specific implementation process is as follows:

[0104] In step 1, after the attitude correction process and scale normalization process of the 3D model, it is judged that the category of the 3D model is a car, and the corresponding category is added with the Chinese label "车届" and the English label "Car".

[0105] In step 2, the training set generation process first generates an icosahedron surrounding the model, performs a surface subdivision on the icosahedron, and takes the generated polyhedron vertices as viewpoints, such as image 3 As shown in , the 2D projection of each 3D model in the training set is obtained at each viewpoint, and the 2D images and v...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an internet image driven automatic selection method of the optimal view of a three-dimensional model. The automatic selection method comprises the following steps: three-dimensional model set preprocessing; image visual angle classifier training: obtaining a classifier used for estimating an observation visual angle of an image, wherein the step specifically comprises two steps of training set generation and image visual angle classifier training; internet image acquisition: collecting the image of a corresponding model in an internet through a great quantity of images uploaded by an image search engine and a social network, wherein the step specifically comprises three steps of internet image capture, irrelevant image filtering and foreground object image extraction; and view voting evaluation: voting to the views corresponding to the three-dimensional model through the internet image, and selecting the view which ranks higher as an optimal view, wherein the step specifically comprises two steps of internet image visual angle estimation and view sorting. The invention can be suitable for various types of three-dimensional models comprising rigid bodies and non-rigid bodies, and conforms to the visual habits of people.

Description

technical field [0001] The invention relates to a computer graphics shape analysis processing method driven by Internet images, which belongs to the technical field of computer graphics, in particular to a method for automatically selecting the optimal view of a three-dimensional model driven by Internet images. Background technique [0002] According to imaging principles and visual computing theory, a 3D model needs to be mapped to a 2D view on the human retina or display screen before it can be viewed and recognized by humans. Human cognition of objects depends on the viewpoint position, and the viewpoint position that enables humans to best recognize and understand the 3D model is called the optimal viewpoint of the 3D model, and the 2D view obtained from the viewpoint mapping is the best Excellent view. The goal of the optimal view selection problem is to find representative views that can represent the main features of a 3D model. The development of computer technolo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/62G06K9/46
Inventor 孙正兴李晨曦宋沫飞王爽
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products