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

A 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: 2022-07-19
TIANJIN UNIV
View PDF7 Cites 0 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
  • A Stereo Image Super-Resolution Reconstruction Method Based on Deep Interactive Learning
  • A Stereo Image Super-Resolution Reconstruction Method Based on Deep Interactive Learning
  • A 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 objectives, technical solutions and advantages of the present invention clearer, the embodiments of the present invention are further described in detail below.

[0027] A Stereo Image Super-Resolution Reconstruction Method Based on Deep Interactive Learning, see figure 1 , the method includes the following steps:

[0028] 1. Constructing the Spatial Feature Extraction Part

[0029] The input left and right views are divided into left and right branches, respectively, and the corresponding spatial feature expression f is extracted through spatial features. 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 this embodiment of the present invention, the single-image super-resolution method MDSR (multiple image super-resolution method) The feature extraction part of scale-depth super-resolution) is used as a spatia...

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. The method includes: dividing the input left and right views into left and right branches to extract corresponding spatial feature expressions through spatial features; Extract complementary information in another viewpoint to enhance the spatial feature representation of left and right views; use mean square error loss function, gradient loss function and disparity loss function to jointly build a multi-loss function mechanism to improve the quality of super-resolution reconstruction of stereo images ; Training a deep interactive learning-based stereo image super-resolution reconstruction network. The invention utilizes the feature expression ability of deep learning, and obtains the spatial correlation of left and right views and the correlation between viewpoints by mining complementary information in stereo images.

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, thereby improving 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 facilitated the development of various computer vision tasks, such as video surveillance, pedestrian detection, and remote sensing image processing. De...

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): 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