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

Stereo image super-resolution reconstruction method based on deep interactive learning

A technology of super-resolution reconstruction and stereo image, applied in the field of stereo image super-resolution reconstruction based on deep interactive learning, can solve the problem of ignoring the spatial correlation of complementary information and the correlation between viewpoints, and achieve the effect of strong feature expression ability

Active Publication Date: 2021-01-05
TIANJIN UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most existing methods learn global consistency relations based on disparity, ignoring the spatial correlation and inter-viewpoint correlation contained in complementary information

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
  • Stereo image super-resolution reconstruction method based on deep interactive learning
  • Stereo image super-resolution reconstruction method based on deep interactive learning
  • Stereo image super-resolution reconstruction method based on deep interactive learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the implementation manners of the present invention will be further described in detail below.

[0027] A stereoscopic image super-resolution reconstruction method based on deep interactive learning, see figure 1 , the method includes the following steps:

[0028] 1. Construct the spatial feature extraction part

[0029] Divide the input left and right views into left and right branches, respectively extract the corresponding spatial features through spatial features to express f l and f r . Each branch can be regarded as a single-image super-resolution task, so the spatial feature extraction can use any single-image super-resolution model to extract features. In the embodiment of the present invention, the single-image super-resolution method MDSR (Multiple The feature extraction part of scale depth super-resolution) is used as the spatial feature extraction module. I...

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 stereo image super-resolution reconstruction method based on deep interactive learning, and the method comprises the steps: dividing an input left view and an input right view into a left branch and a right branch, and extracting corresponding spatial feature expressions through spatial features; extracting complementary information in another viewpoint through an interaction part and adopting the complementary information for enhancing spatial feature expression of the left view and the right view; adopting a mean square error loss function, a gradient loss functionand a parallax loss function for jointly constructing a multi-loss function mechanism, and adopting the multi-loss function mechanism for improving stereo image super-resolution reconstruction quality; and training a stereo image super-resolution reconstruction network based on deep interactive learning. According to the method, the spatial correlation and the inter-viewpoint correlation of the left view and the right view are obtained by mining complementary information in the stereo image by utilizing the feature expression capability of deep learning.

Description

technical field [0001] The invention relates to the fields of deep learning and image super-resolution reconstruction, in particular to a stereoscopic image super-resolution reconstruction method based on deep interactive learning. Background technique [0002] As a basic image processing technique, super-resolution reconstruction has attracted more and more scholars to conduct extensive research. The purpose of super-resolution reconstruction is to predict the missing high-frequency information in low-resolution images, so as to improve the resolution of low-resolution images. Since super-resolution reconstruction can restore texture details in images, it can be applied to many image processing tasks, such as image restoration, image enhancement, and image compression. In addition, super-resolution reconstruction has also promoted the development of various computer vision tasks, such as video surveillance, pedestrian detection, and remote sensing image processing. Depend...

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): G06T3/40G06N3/04
CPCG06T3/4053G06N3/045
Inventor 雷建军张哲范晓婷刘娟桑新柱彭勃
Owner TIANJIN 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