Method and device for converting single picture from two-dimension to three-dimension semi-automatically by adopting optimization technology

A semi-automatic, conversion method technology, applied in the field of multimedia signal processing and image, which can solve problems such as strong dependence and complex input

Inactive Publication Date: 2012-10-10
SHANDONG UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the shortcomings of the current algorithm, such as complex user input and strong dependence of the algorithm on other algorithms, the present invention proposes a semi-automatic 2D to 3D conversion method for a single image based on an optimization method

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 and device for converting single picture from two-dimension to three-dimension semi-automatically by adopting optimization technology
  • Method and device for converting single picture from two-dimension to three-dimension semi-automatically by adopting optimization technology
  • Method and device for converting single picture from two-dimension to three-dimension semi-automatically by adopting optimization technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In the semi-automatic two-dimensional to three-dimensional conversion method of the present invention, the user is first required to manually select a number of representative pixels representative in depth according to the structural characteristics of the picture scene and the depth characteristics of the objects in the scene through visual observation, and provide the selected Set the corresponding depth value on behalf of the pixel. During specific implementation, the depth value of some representative pixels can be set for the picture on the computer display screen by graffiti, and then the present invention models the depth calculation of the picture as a constrained optimization problem, and solves the problem by the least squares algorithm. question.

[0017] figure 1 is a friendly user interface developed according to the present invention. This interface can not only assist users to conveniently and quickly set some depth values ​​representing pixels, but al...

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 provides a method and a device for converting a single picture from two-dimension to three-dimension semi-automatically by adopting an optimization technology. The method comprises the following steps of: first, setting a plurality of depth values representing pixels by a user; then, modeling a depth map solving problem of the overall map into a constrained optimization problem; and finally, solving an optimum solution of the optimization problem by adopting a least square algorithm. By the semiautomatic conversion method provided by the invention, a high-quality depth map can be obtained by only a small amount of user participation, and a high-quality three-dimensional picture can be converted, so that the method and the device have a very wide application value in the field of three-dimensional content generation.

Description

technical field [0001] The invention relates to a semi-automatic conversion technology from a two-dimensional picture to a three-dimensional picture, and belongs to the technical field of image and multimedia signal processing. Background technique [0002] Due to the shortage of 3D video content, the conversion technology of 2D video to 3D video has become more and more research hotspot. Although the automatic conversion technology does not require manual participation, the 3D effect obtained cannot meet people's requirements. Compared with it, the semi-automatic conversion technology can obtain a more accurate depth map by adding a small amount of manpower. Therefore, this method generally accepted. [0003] In a semi-automatic 2D video to 3D video conversion system, the general approach is: first extract key frames from the entire video, then manually set the depth of key frames, and finally, according to the correlation between non-key frames and key frames, through dep...

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): G06T3/00G06T15/00
Inventor 刘琚王地长生曹广昊孙建德任艳楠葛川
Owner SHANDONG 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