Three-dimensional object normal vector, geometry and material acquisition method based on neural network

A neural network and three-dimensional object technology, applied in the processing of 3D images, image data processing, instruments, etc.

Active Publication Date: 2019-12-13
ZHEJIANG UNIV +1
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although there are some previous works that collect the geometric and material information o

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
  • Three-dimensional object normal vector, geometry and material acquisition method based on neural network
  • Three-dimensional object normal vector, geometry and material acquisition method based on neural network
  • Three-dimensional object normal vector, geometry and material acquisition method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0076] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0077] The present invention provides a neural network-combined acquisition method based on the idea of ​​"actively irradiating a number of specific patterns on an object, simultaneously collecting photos, and obtaining the normal vector of the object by calculating the obtained photos". Further, the method uses the obtained normal vector to optimize the model of the object. This method can also obtain material feature information while obtaining the normal vector. Finally, high-quality geometric and material collection results are obtained jointly. The specific implementation of the three parts is described in detail below:

[0078] 1. A method for obtaining the normal vector of a three-dimensional object based on a neural network, the me...

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 a three-dimensional object normal vector, geometry and material acquisition method based on a neural network, and provides an acquisition method combined with the neural network on the idea of 'actively irradiating an object with a plurality of specific patterns. while collecting a picture and calculating the obtained picture to obtain an object normal vector '. Further, the method uses the obtained normal vector to optimize the model of the object. The material characteristic information can be obtained while the normal vector is obtained. Finally, a high-quality geometric and material acquisition result is obtained through combination. The number of illumination patterns obtained through the method is small, the obtained normal vector is high in precision, and themethod is not limited to a certain specific collection device.

Description

technical field [0001] The invention relates to a method for obtaining a normal vector of a three-dimensional object based on a neural network, a geometry optimization method and a material acquisition method based on the method, and belongs to the fields of computer graphics and computer vision. Background technique [0002] Digitizing real objects has long been a difficult problem in computer graphics / vision. Currently, digitized real objects can be represented by a three-dimensional grid and a six-dimensional spatially varying bidirectional reflectance distribution function (SVBRDF). Based on this representation, the appearance of objects under any viewing angle and lighting conditions can be well rendered. [0003] However, how to simultaneously obtain the reflection information and geometric information of objects with high efficiency and high quality is still a big challenge. On the one hand, high quality requires that as many observations as possible can be obtained...

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): G06T15/00G06T15/04G06T15/50
CPCG06T15/005G06T15/04G06T15/50
Inventor 吴鸿智周昆康凯彰
Owner ZHEJIANG 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap