Method for complementing object shape in RGBD image

A technology in the shape and image of objects, applied in the field of 3D geometric modeling, it can solve problems such as loss of geometric details, and achieve the effect of simplifying complex processes

Active Publication Date: 2016-08-31
ZHEJIANG UNIV +1
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such methods can handle a large number of general objects, but geometric details are often lost

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
  • Method for complementing object shape in RGBD image
  • Method for complementing object shape in RGBD image
  • Method for complementing object shape in RGBD image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0066] The inventor has implemented the embodiment of the present invention on a desktop computer equipped with an Intel I5-4430 central processing unit, Nvidia GeForce GTX760 graphics card and 16GB memory.

[0067] The inventor used Microsoft Kinect to collect RGBD images of objects in multiple categories (such as chairs, tables, statues, bicycles, containers, toys, etc.), and used the public data set released by the US UIUC to test the experimental results of the invention. The results show that, in our current hardware configuration, the present invention can complement a large amount of geometric information missing from objects in a single RGBD image in a relatively short time. Although the initial solution obtained by the data-driven method is very different from the input data in terms of geometry and topology, the optimization algorithm based on volume matching of the present invention can be very good by combining surface confidence constraints, visibility constraints and...

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 method for complementing an object shape in an RGBD image, comprising steps of adopting a pre-cut object in a single RGBD image as an input, estimating a preliminary complete shape in virtue of a same-category three-dimensional model in a database, and obtaining an optimal complete shape through an optimization algorithm based on block matching. The method for complementing the object shape in the RGBD image simplifies a complex process of three-dimensional data collection, user does not need to hold an EGBD camera to surround the object for multiple scanning, instead, the user only needs to push one button just like taking picture. In the backstage, the method of the invention can perform automatic completion on the data of the single RGBD image shot by the user, the shape of the object after completion does not only meet the expectation of the user from the appearance, the local details are consistent with the detail in a visible part of an RGBD image.

Description

Technical field [0001] The present invention relates to the field of three-dimensional geometric modeling, in particular to a method for completing geometric shapes based on a single RGBD image. Background technique [0002] Three-dimensional shape completion technology is widely used in the field of incomplete data recovery. Early work includes smoothing and mesh reconstruction technology (S. Bischoff, et al. "Automatic restoration of polygonmodels," ACMTrans.Graph., 24(4):1332–1352.), scattered data fitting technology (S. Shalom) ,A.Shamir,H.Zhang,and D.Cohen-Or,"Cone carving for surface reconstruction,"ACM Trans.Graph.,29(5).) is used to deal with the missing holes of smooth surfaces, but for complex Missing areas are more difficult to get better results. Content-based completion technology explores self-similarity to use its own texture or repeated elements to complement the missing areas of objects (A.Sharf, M.Alexa, and D.Cohen-Or, "Context-based surfacecompletion," ACM ...

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): G06T17/10G06T15/08
CPCG06T15/08G06T17/10
Inventor 周昆邵天甲
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