Unlock instant, AI-driven research and patent intelligence for your innovation.

A no-reference image quality assessment method for view synthesis

A technology for synthesizing images and quality evaluation, applied in the field of objective visual quality evaluation of virtual perspective synthesis, can solve the problems of inability to obtain original images, ignoring perspective image distortion, restricting the application of full reference methods, etc., achieving good cross-database performance and scalability. strong effect

Active Publication Date: 2022-05-03
CHINA UNIV OF MINING & TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above existing synthetic image quality evaluation methods have the following defects: First, each method is designed for one type of distortion, while ignoring the other distortion brought in the perspective image synthesis process
In reality, the original image is often not available, which restricts the application of existing full-reference methods

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 image quality assessment method for view synthesis
  • A no-reference image quality assessment method for view synthesis
  • A no-reference image quality assessment method for view synthesis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] The present invention will be further described below in conjunction with the accompanying drawings.

[0070] figure 1 Shown is a flowchart of the present invention, as can be seen from the figure: the overall process of the present invention is divided into four modules:

[0071] 1. Scale space expression 2. DoG model establishment 3. Feature extraction 4. Training quality evaluation model. These four steps are described in detail below:

[0072]Module 1: Scale Space Expression—For a perspective synthesis image, the Gaussian low-pass filter is used to filter the image multiple times to construct the scale space of the image.

[0073] Module 2: Establishment of the DOG model—the difference between images of adjacent scales is obtained to obtain the difference image of the Gaussian filter, that is, the DoG image.

[0074] Module 3: Feature extraction—feature extraction is carried out in the DoG image and the last scale image, and the features specifically extracted in...

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 no-reference image quality evaluation method oriented to perspective synthesis. The method quantifies the distortion in the synthesized image by analyzing the characteristics of two types of distortion and designing features: firstly, the distortion caused by the edge damage of the image and the difference in texture Naturalness is quantified and corresponding features are extracted. Then use the machine learning method to integrate the features, so as to train a quality evaluation model that can evaluate the distortion caused by the entire synthesis process. The present invention overcomes two disadvantages of the existing method: (1) The existing method can only evaluate one type of distortion in the synthesis process, while the method can effectively evaluate two types of distortion in the entire synthesis process. (2) Most of the existing methods are full-reference methods, that is, they must provide the original undistorted image in order to evaluate the quality of the distorted image, while the method in this paper is a no-reference method, which has a wider application prospect.

Description

technical field [0001] The invention relates to an objective visual quality evaluation method for virtual viewing angle synthesis, in particular to a reference-free image quality evaluation method for viewing angle synthesis. Background technique [0002] View synthesis is to use texture image and depth image to synthesize a new view image. View synthesis technology is widely used in fields such as multi-view video and free-view TV [1]. The quality evaluation of the synthesized views can quantitatively evaluate the quality of the view synthesis technique, and can also be used to optimize the synthesis technique. Furthermore, the quality evaluation of view-synthesized images directly affects the success of these applications. Therefore, the quality evaluation for view synthesis is of great significance. [0003] Distortions in synthetic perspective fall into two main categories. The first category is the traditional distortion brought by the acquisition, processing and tr...

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): G06T7/00
CPCG06T7/0002G06T2207/10028G06T2207/20024G06T2207/20221G06T2207/30168
Inventor 李雷达周玉卢兆林
Owner CHINA UNIV OF MINING & TECH