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

A Method for Evaluating the Image Quality of View Synthesis

A technology for synthesizing images and perspectives, applied in image analysis, image enhancement, image data processing and other directions, it can solve the problems of inability to accurately extract geometric distortion areas and unsatisfactory performance, and achieve excellent performance and performance.

Active Publication Date: 2021-06-29
XIDIAN UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The reason is that the view synthesis image contains both global blur distortion and local geometric distortion, while methods [8]-[11] ignore the influence of local geometric distortion in view synthesis images on visual quality; methods [12]-[ 15] Although the influence of local geometric distortion is considered, it cannot accurately extract the geometric distortion area in the perspective synthesis image, resulting in its performance is still not ideal

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 Method for Evaluating the Image Quality of View Synthesis
  • A Method for Evaluating the Image Quality of View Synthesis
  • A Method for Evaluating the Image Quality of View Synthesis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066]The distortions caused by the DIBR perspective drawing process are mainly global fuzzy distortion and local geometric distortion. Among them, the local geometric distortion is mainly distributed on the edge of the instance in the image. How to evaluate the global blur and local geometric distortion in the image is the key technical problem to be solved by the present invention. This technical problem is embodied in two aspects: 1. How to describe the global blur and distortion in the synthetic perspective image; 2. How to locate the synthetic perspective image , and quantitatively describe the geometric distortion at the edge of the instance.

[0067] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0068] figure 1 It is a flowchart of the present invention, as shown in the figure, the present invention includes three modules:

[0069] Module 1: quantify the global blur distortion in the im...

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 proposes a method for evaluating the quality of a synthetic view image, which includes four steps: (1) using a superpixel segmentation method to synthesize a synthetic view image I to be evaluated. s and I s The original image of I r Separately divided into K superpixels; (2) Composite image I s Carry out global fuzzy evaluation and get the global fuzzy evaluation quality score Q 1 ; (3) Locate the instance in the view synthesis image, and quantitatively describe the geometric distortion at the edge of the instance, and obtain the local geometric distortion quality score Q 2 ; (4) According to Q 1 and Q 2 Generating Perspective Synthesis Image I s quality score. The present invention can more accurately evaluate global blur and local geometric distortion in view synthesis images.

Description

technical field [0001] The invention relates to the technical field of image quality evaluation, in particular to a method for evaluating the image quality of view synthesis. Background technique [0002] Multi-view and free-view technologies are important frontier research fields of visual media and have broad application prospects. In the application of multi-view and free view, the most critical technology and difficulty is the synthesis of virtual view [1] . This is because in the actual environment, due to the constraints of hardware cost and network bandwidth, it is often only possible to arrange cameras at limited viewing angles to obtain texture images and depth images. After encoding and transmission, these existing viewing angles can be used at the receiving end. The information synthesizes the remaining views (virtual views). The depth image based rendering method (Depth Image Based Rendering, DIBR) is currently the most commonly used method for virtual perspec...

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): G06T7/00G06T5/00
CPCG06T7/0002G06T2207/30168G06T5/80
Inventor 李雷达周玉吴金建李甫石光明
Owner XIDIAN 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

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