Image completion method and device

A completion and image technology, applied in the field of image processing, can solve problems such as poor completion effect, and achieve the effect of speeding up learning, increasing image pixels, and improving resolution

Active Publication Date: 2017-09-05
BEIJING XIAOMI MOBILE SOFTWARE CO LTD
View PDF4 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the development of the times, image completion is applied more and more, for example, the details are lost after image enlargement, and the image is partially damaged. However, the current solution only completes through image search, matching, and filtering. Poor completion

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
  • Image completion method and device
  • Image completion method and device
  • Image completion method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0099] figure 1 is a flow chart of an image completion method shown according to an exemplary embodiment, such as figure 1 As shown, the image completion method is used in an image completion device, which can be applied to terminals and servers, and the method includes the following steps 101-104:

[0100] In step 101, an n-layer Gaussian pyramid is generated according to the image to be repaired.

[0101] Here, n is a positive integer.

[0102] Obtain the mask (mask) image corresponding to the image to be repaired, mark the part that needs to be repaired as 0, and mark the part that does not need to be repaired as 255, and construct a Gaussian pyramid of the image to be repaired and the corresponding mask image until there is no 0 in the mask. Here, n is a positive integer.

[0103] In step 102, the images of each layer in the n-layer Gaussian pyramid are completed by using a block matching method, and the completed real images of each layer are obtained.

[0104] Start ...

Embodiment 2

[0135] figure 2 is a flow chart of an image completion method shown according to an exemplary embodiment, such as figure 2 As shown, the image completion method is used in an image completion device, and the device can be applied to terminals and servers. The method includes the following steps 201-205:

[0136] In step 201, an n-layer Gaussian pyramid is generated according to the image to be repaired.

[0137] Here, n is a positive integer.

[0138] In step 202, the images of each layer in the n-layer Gaussian pyramid are completed by using a block matching method, and the completed real images of each layer are obtained.

[0139] In step 203, a discriminant network of an adversarial network that satisfies the requirements of the objective function is trained through the nth layer image and the real image of each layer.

[0140] In step 204, a generation network that meets the requirements of the objective function is trained through the nth layer image, the real image ...

Embodiment 3

[0144] image 3 is a flow chart of an image completion method shown according to an exemplary embodiment, such as image 3 As shown, the image completion method is used in an image completion device, and the device can be applied to terminals and servers. The method includes the following steps 301-320:

[0145] In step 301, an n-layer Gaussian pyramid is generated according to the image to be repaired.

[0146] In step 302, randomly upsample from the nth layer image of the n-layer Gaussian pyramid to obtain an nth generated image with the same resolution as the nth layer image.

[0147] In step 303, the jth generated graph is acquired.

[0148] In step 304, the block matching method is used to complement the image at the jth layer of the n-layer Gaussian pyramid to obtain the real image at the jth layer.

[0149] In step 305, the jth layer real map and the jth generated map are input into the improved discriminant network to obtain a first judgment result.

[0150] In ste...

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 disclosure relates to an image completion method and device. The method includes the following steps: generating n layers of Gauss pyramids on the basis of an image to be restored, n being a positive integer; through a block matching method, completing images of each of the n layers of Gauss pyramids, and obtaining an actual image of each layer after completion; generating a generative network of an adversarial network on the basis of the n image of the n layers of Gauss pyramids and the actual images of all the layers; and on the basis of the n image and the generative network, completing the image to be restored, and obtaining a completed image after completion. According to the technical scheme, the generative network is obtained through a Gauss pyramid of the image to be restored, the actual images of all layers of Gauss pyramids and the adversarial network, so a clear and complete image high in resolution can be generated quickly. Therefore, the resolution of the completed image is improved, learning about the generative network is accelerated, and a more real image can be obtained.

Description

technical field [0001] The present disclosure relates to the field of image processing, in particular to an image complement method and device. Background technique [0002] With the development of the times, image completion is applied more and more, for example, the details are lost after image enlargement, and the image is partially damaged. However, the current solution only completes through image search, matching, and filtering. Completion doesn't work well. Contents of the invention [0003] Embodiments of the present disclosure provide an image complement method and device. Described technical scheme is as follows: [0004] According to the first aspect of the embodiments of the present disclosure, an image complement method is provided, including: [0005] According to the image to be repaired, an n-layer Gaussian pyramid is generated, and the n is a positive integer; [0006] Completing the images of each layer in the n-layer Gaussian pyramid by a block match...

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): G06T5/00
CPCG06T5/005G06T2207/20021G06T2207/20081G06T2207/20084
Inventor 张水发刘鹏张波
Owner BEIJING XIAOMI MOBILE SOFTWARE CO LTD
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