Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Dense three-dimensional object reconstruction method based on learning efficient point cloud generation

A three-dimensional object, effective point technology, applied in the field of target reconstruction

Inactive Publication Date: 2017-12-15
SHENZHEN WEITESHI TECH
View PDF0 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To solve the problem of reconstructing target objects under different viewing angles, the purpose of the present invention is to provide a dense 3D object reconstruction method based on learning effective point cloud generation, and propose a new framework for generating 3D images based on 2D convolution

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
  • Dense three-dimensional object reconstruction method based on learning efficient point cloud generation
  • Dense three-dimensional object reconstruction method based on learning efficient point cloud generation
  • Dense three-dimensional object reconstruction method based on learning efficient point cloud generation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be further described in detail below with reference to the drawings and specific embodiments.

[0033] figure 1 It is a system flowchart of a dense three-dimensional object reconstruction method based on learning effective point cloud generation in the present invention. It mainly includes object reconstruction system; structure parameter setting; training method.

[0034] Wherein, the object reconstruction system includes a structure generation device, a pseudo-compensation device and a structure optimization device.

[0035] The structure generation device uses a two-dimensional convolution operation to predict the surface geometric parameters of a three-dimensional object, specifically given a three-dimensional accurate transformation matrix (R 1 ,t 1 )…(R N ,t N ), then ea...

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 present invention provides a dense three-dimensional object reconstruction method based on learning efficient point cloud generation. The main content of the method comprises: an object reconstruction system, structure parameter setting and a training method. The process of the method comprises: an encoder is employed to extract an input image to an abstract representation space and perform union two-dimensional projection, a structure generator is employed to generate point cloud on the basis of two-dimensional convolution; up-sampling operation is employed to enlarge the image resolution, after the point cloud is projected to a two-dimensional plane, and the max-pooling operation is employed to recover the image to the original resolution to obtain a reconstruction object view. The dense three-dimensional object reconstruction method based on learning efficient point cloud generation can process three-dimensional views with different visual angles, and a pseudo compensation device is improved to solve the pixel superposition problem so as to improve the recognition rate of object reconstruction and the generation correct rate in a new perspective.

Description

technical field [0001] The invention relates to the field of target reconstruction, in particular to a dense three-dimensional object reconstruction method based on effective point cloud generation through learning. Background technique [0002] Object reconstruction analysis is an important topic in the field of computer vision. With the continuous development of software and hardware conditions, the demand for 3D scene restoration applications is increasing. The task of 3D reconstruction technology is to obtain 3D geometric information from images (single or multiple images) through certain modeling operations, plus calibration, matching and other technologies to obtain image 3D scene models and data. 3D visualization and reconstruction technology has been widely used in various fields of society, such as medical imaging, geological and mineral exploration, street view recording, navigation technology, etc. Even emerging fields such as object recognition and modeling in o...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T15/10
CPCG06T15/10G06T2207/10028G06T2207/20081G06T2215/06
Inventor 夏春秋
Owner SHENZHEN WEITESHI TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com