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

A method for superdividing stereoscopic images

A stereoscopic image and super-resolution technology, which is applied in the field of image editing, can solve the problems of increased calculation and loss of high-frequency content of the image, and achieve the effects of increased resolution, high research and application value, and clear visual quality

Active Publication Date: 2018-12-25
FUDAN UNIV
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the high-frequency content in the image will be lost, and the calculation of overlapping slices will increase the amount of calculation

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 superdividing stereoscopic images
  • A method for superdividing stereoscopic images
  • A method for superdividing stereoscopic images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] For a pair of low-resolution stereo images, perform super-resolution processing, the specific process is as follows figure 1 shown.

[0068] The specific steps are:

[0069] For existing low-resolution stereo images (LR left , LR right ), first input it into the optical flow estimation network F OE , the specific steps are as figure 2 Shown:

[0070] Extract the luminance channel Y of the left and right images left , Y right , and concatenate them to get Y; secondly, pass Y through a convolution layer with a size of 3×3×64 to generate a feature map f; then pass f through a GRU convolution block in turn, a 1×1 convolution Layer, a maximum pooling operation outputs the feature f 1 ;Repeat the GRU convolution block, 1×1 size convolution layer and a maximum pooling operation three times, and generate the feature f each time 1 , f 2 and f 3 ; set the feature f 3 Amplify its feature dimension through bilinear interpolation, and then generate a feature f through a...

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 belongs to the technical field of image editing, in particular to a method for superdividing stereoscopic images. The method of the invention comprises the following steps of: the position information of the left and right pictures is estimated by adopting an optical flow estimation network; high-resolution image is reconstructed by image super-division network; when reconstructing the left image in a stereoscopic image, not only the local redundancy and structural correlation of the pixels in the image are utilized, combined with the characteristics of correlation and complementarity between the left and right images of the stereoscopic image, more high-frequency information lost in the low-resolution left image is obtained to recover the content of the original image, and the effect of enhancing the rich detail texture of the image resolution is achieved. Experimental results show that this method can effectively improve the resolution of stereoscopic images, and make stereoscopic images have clearer visual quality, richer content and higher research and application value.

Description

technical field [0001] The invention belongs to the technical field of image editing, and relates to an image super-resolution method, and more specifically, relates to a method for performing super-resolution on a stereoscopic image. Background technique [0002] Traditional image super-resolution technology is basically a research branch of image quality enhancement technology. It is a modern image processing technology with high scientific research value and wide application fields. [0003] Image resolution is an important indicator of image quality. The higher the resolution, the finer the details, the better the quality, and the richer the information provided by the image. Therefore, images with higher resolution have important application value and research prospects in various fields. However, due to restrictions or interference in the process of image collection, storage, and transmission, there are varying degrees of quality degradation. Usually the most direct...

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
CPCG06T3/4076G06T2207/10012G06N3/045
Inventor 颜波巴合提亚尔·巴热马晨曦
Owner FUDAN 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