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

Multi-view-point image super-resolution method based on deep information

A multi-view image and depth information technology, applied in image communication, stereo systems, electrical components, etc., can solve problems such as increasing computational complexity, avoid edge artifacts, improve quality, and reduce computational complexity.

Inactive Publication Date: 2014-10-01
SHANDONG UNIV
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The defect of this method is that the reverse projection method is used to detect the validity of the pixel mapping relationship between different viewpoints, only the depth information of the image is used, and edge artifacts will occur due to the inaccurate edge depth of foreground objects; secondly, in order to reverse Projection requires two mappings between viewpoints, which increases the computational complexity

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
  • Multi-view-point image super-resolution method based on deep information
  • Multi-view-point image super-resolution method based on deep information
  • Multi-view-point image super-resolution method based on deep information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The invention proposes a multi-viewpoint image super-resolution method based on depth information. The method adopts the effective detection of the pixel mapping relationship between joint viewpoints based on depth and chroma, and can effectively eliminate edge artifacts and improve the quality of super-resolution reconstructed images when performing super-resolution reconstruction of low-resolution viewpoints.

[0035] refer to figure 1 , the specific implementation steps of the present invention are as follows:

[0036] Step 1: Input the depth map D of viewpoint n respectively n ,Such as figure 2 As shown, the low-resolution color map of viewpoint n Such as image 3 As shown, the magnification is 2 times, and the depth map D of the viewpoint k k ,Such as Figure 4 As shown, the high-resolution color map V of viewpoint k k ,Such as Figure 5 shown;

[0037] Step 2: Low-resolution color map for viewpoint n Perform 2 times upsampling, and use a 6-tap filter ...

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 multi-view-point image super-resolution method based on deep information. The multi-view-point image super-resolution method mainly solves the problem that in the prior art, the edge artifact phenomenon occurs when super-resolution reconstruction is conducted on a low-resolution view point image. The method includes the steps of mapping a high-resolution colored image of a view point k on the image position of a view point n according to a pinhole camera model through the deep information, related camera parameters and a backward projection method, conducting effectiveness detection based on pixel mapping relations between the joint view points of the depth differences and the color differences on the projected image, only reserving pixel points conforming to effectiveness detection so as to prevent luminance differences between different view points from influencing illumination regulation conducted on the colored image of the view point k in advance, separating out high-frequency information of the projected image, and adding the high-frequency information to the image obtained after the low-resolution colored image of the view point n is sampled so as to obtain a super-resolution reconstructed image of the view point n. By means of the method, the edge artifact phenomenon is effectively relieved when super-resolution reconstruction is conducted on the low-resolution view point, and the quality of the super-resolution reconstructed image is improved.

Description

technical field [0001] The invention relates to a multi-viewpoint image super-resolution method based on depth information, and belongs to the technical field of image processing. Background technique [0002] At present, the acquisition and playback technology of multi-viewpoint video has made great progress, and 3D stereoscopic video has become a promising application. However, with the development of stereoscopic video, many problems have arisen, such as the increase in the amount of transmitted data and the burden of computational complexity. The solution is to adopt a mixed-resolution multi-view video architecture, down-sample the color images of individual viewpoints at the sending end to obtain a low-resolution form, and restore its high-frequency components through super-resolution technology at the receiving end to effectively reduce the Transfer data volume and computational complexity. How to effectively recover the high-frequency information of the low-resoluti...

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): H04N13/00H04N15/00
Inventor 刘琚伯君孙国霞赵悦葛菁王梓
Owner SHANDONG UNIV
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