Three-dimensional image super-resolution reconstruction method based on cyclic interaction

A super-resolution reconstruction and stereoscopic image technology, which is applied in graphics and image conversion, image data processing, instruments, etc., can solve the problem that complementary information is not fully exploited, and achieve the effect of strong stereoscopic image feature expression ability

Active Publication Date: 2021-10-15
TIANJIN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the complementary information between the features of different levels of the left and right viewpoints from different levels of the network has not been fully exploited

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
  • Three-dimensional image super-resolution reconstruction method based on cyclic interaction
  • Three-dimensional image super-resolution reconstruction method based on cyclic interaction
  • Three-dimensional image super-resolution reconstruction method based on cyclic interaction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] 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.

[0036] 1. Build a multi-layer spatial feature extraction module

[0037] For the left and right views of the input, the embodiment of the present invention divides two branches to construct a multi-layer spatial feature extraction module to obtain multi-layer spatial feature expression and

[0038] Specifically, the multi-layer spatial feature extraction modules of the two branches share parameters, both of which are composed of cascaded p-layer residual groups, and the features output by the p-th layer residual group are denoted as and Among them, each residual group consists of cascaded multiple residual blocks and a channel attention.

[0039] 2. Queue reorganization conversion

[0040] Multi-Layer Spatial Feature Representation for Left and Right Viewpoints and ...

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 three-dimensional image super-resolution reconstruction method based on cyclic interaction, which comprises the following steps: recombining multilayer features of left and right viewpoints into left and right sequences through queue recombination conversion, and recombining arrangement following the sequence of the features from a shallow layer to a deep layer; building a circular interaction module, enhancing multi-layer features of left and right viewpoints interactively through a circular structure, wherein the circular interaction module is composed of a circular interaction unit, and the circular interaction unit is composed of two interaction units and a jump connection; through a multi-propagation strategy, circularly interactively inputting multilayer features of left and right viewpoints in a sequence, learning dependency between viewpoints to enhance the features, and further obtaining final circular interaction enhanced features; enhancing features based on circulation interaction, using sub-pixel convolution to improve feature resolution, and using n * n convolution to reconstruct the features into high-resolution left and right views; and building a multi-loss function mechanism by using a correlation loss function, a difference loss function and an L1 loss function, so that the super-resolution reconstruction quality of the three-dimensional image is improved.

Description

technical field [0001] The present 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 loop interaction. Background technique [0002] With the continuous popularization of stereoscopic display devices, the display quality of stereoscopic images has attracted more and more attention. In stereoscopic display, high-resolution stereoscopic images can provide people with a detailed and realistic stereoscopic viewing experience, so it is very important. Stereo image super-resolution reconstruction aims at the reconstruction of high-resolution stereo images by predicting the high-frequency information missing in low-resolution stereo images. Stereo image super-resolution reconstruction can recover texture details of left and right viewpoints, making it widely used in various image processing techniques such as depth estimation, viewpoint synthesis and imag...

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
IPC IPC(8): G06T3/40
CPCG06T3/4053G06T3/4046
Inventor 雷建军张哲彭勃朱杰范晓婷
Owner TIANJIN 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