Mixed resolution multi-view video super-resolution method based on low-rank prior information

A technology of multi-view video and prior information, applied in the field of image and video processing, can solve the problem of relying on depth maps, and achieve the effect of suppressing block noise

Active Publication Date: 2020-11-03
NANKAI UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of this invention is to solve the problem that the existing hybrid multi-viewpoint video reconstruction method is very dependent on the depth map, and propose an effective reconstruction 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
  • Mixed resolution multi-view video super-resolution method based on low-rank prior information
  • Mixed resolution multi-view video super-resolution method based on low-rank prior information
  • Mixed resolution multi-view video super-resolution method based on low-rank prior information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0019] refer to figure 1 , which represents the super-resolution reconstruction flow chart of mixed multi-view video based on low-rank prior. The method of reconstructing the middle low-resolution video from two high-resolution videos is as follows:

[0020] a. Input low-resolution video and adjacent high-resolution video: such as figure 1 As shown in the input in , the input viewpoint c tar One low-resolution video, input viewpoint c 1 and c 2 Two high-resolution videos, for each frame of the low-resolution video, use the high-resolution video frame in space and time to reconstruct. Specifically, when reconstructing the t-th low-resolution video frame, the viewpoint c is required 1...

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 mixed-resolution multi-view video super-resolution method based on low-rank prior information, and belongs to the technical field of image and video processing. The mixed-resolution multi-view video is composed of multiple paths of multi-view videos and comprises multiple paths of low-resolution videos and multiple paths of high-resolution videos, and the proposed super-resolution method aims to reconstruct the low-resolution videos by using texture and other information of the high-resolution videos and take the low-rank prior of the image video as a constraint condition at the same time. According to the method, a new hybrid multi-view super-resolution method is provided, the method considers that a plurality of similar information is contained among multi-viewvideos, the method makes full use of texture and other information of high-resolution videos based on the idea of manifold embedding, and noise is suppressed by using low-rank prior information. According to the method, the texture and other information of the high-resolution video are fully utilized, the noise is effectively suppressed, and the low-resolution video is effectively reconstructed.

Description

technical field [0001] The invention belongs to the technical field of image and video processing, and in particular relates to a multi-view video super-resolution method based on low-rank prior information and manifold embedding. Background technique [0002] 3D movies\games, virtual reality and other technologies will involve multi-viewpoint video, but due to hardware and bandwidth limitations, often multi-viewpoint multi-channel videos are not all high-resolution, but usually can only obtain both high-resolution This rate also includes low-resolution multi-channel hybrid multi-view video. After obtaining the mixed multi-view video, in order to meet certain requirements, it is necessary to reconstruct the low-resolution video based on the obtained mixed multi-view video, that is, perform super-resolution reconstruction for the low-resolution video. [0003] Image\video super-resolution is a basic task in computer vision. Its purpose is to reconstruct a corresponding high-...

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): G06T3/40
CPCG06T3/4053
Inventor 卢少平李森茂
Owner NANKAI 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