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

A No-Reference Quality Assessment Method for 3D Image/Video

A 3D image and reference quality technology, applied in image communication, television, electrical components, etc., can solve problems such as the introduction of DIBR, the difficulty of obtaining reference images, and the inability to automatically play 3D images, and achieve the effect of reducing computational intensity

Active Publication Date: 2019-09-13
WISCOM SYSTEM CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the rapid development of 3D video applications, there are more and more related studies on the evaluation of 3D image and video quality, including quality evaluation methods with reference and without reference: M.J.Chen proposed a full-reference method for dual-view 3D images The quality assessment method; Z.Sazzad proposed a no-reference quality assessment method for dual-view 3D images, but this assessment method cannot meet the needs of automatic playback of 3D images, so that the receiver has to use the DIBR algorithm based on depth information creates the necessary free-viewpoint views, unfortunately DIBR introduces entirely new quality artifacts; E.Bosc proposed a full-reference quality assessment method for ordinary 3D images, but due to the difficulty of obtaining a reference at the receiver end of a 3d TV system M.Solh proposed a method for no-reference quality assessment of 3D images presented by a single frame image plus a depth map (2d+z), but the disadvantage of this method is that it cannot use depth Predicting the relationship between different views in the multi-view 3D image (MVD) format of the graph

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
  • A No-Reference Quality Assessment Method for 3D Image/Video
  • A No-Reference Quality Assessment Method for 3D Image/Video
  • A No-Reference Quality Assessment Method for 3D Image/Video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0023] This patent proposes a method for evaluating the quality of a 3D image based on the MVD format without reference. This method is for such as figure 1 The shown 3D TV system is designed for real-time quality monitoring. We named this evaluation method Synthesized View Comparison Method (SVC), which uses the DIBR algorithm to generate virtual views of the left and right views at the same viewpoint, and compares the differences between the two virtual views. A comparison was made. In our implementation, Structural Similarity Scale (SSIM), a traditional 2D image quality assessment method, is adopted to measure the difference between two virtual views. If the left and right view texture information and depth information are flawless, there are basically no structural differences between these two virtual views. Therefore, by comparing these tw...

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 no-reference quality evaluation method of a three-dimensional image / video. The input of the three-dimensional image in an MVD format is accepted, and the three-dimensional image comprises a left view, a depth view of the left view, a right view and a depth view of the right view. The quality evaluation process is as follows: (1) generating a virtual view I1 of the left view at a binocular central position, and generating a virtual view I2 of the right view at the binocular central position by adopting a DIBR algorithm; and (2) calculating the structural similarity ofI1 and I2 by using an SSIM algorithm, and outputting the value as a quality evaluation value of the three-dimensional image.

Description

technical field [0001] The invention relates to a no-reference quality assessment method for 3D images / videos, in particular to a no-reference quality assessment method for 3D images / videos presented in MVD format. Background technique [0002] Traditional 2D image and video quality assessment methods have been studied for many years. With the rapid development of 3D video applications, there are more and more related studies on the evaluation of 3D image and video quality, including quality evaluation methods with reference and without reference: M.J.Chen proposed a full-reference method for dual-view 3D images The quality assessment method; Z.Sazzad proposed a no-reference quality assessment method for dual-view 3D images, but this assessment method cannot meet the needs of automatic playback of 3D images, so that the receiver has to use the DIBR algorithm based on depth information creates the necessary free-viewpoint views, unfortunately DIBR introduces entirely new qua...

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 Patents(China)
IPC IPC(8): H04N17/00
Inventor 马小骏顾晓东
Owner WISCOM SYSTEM CO LTD
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