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

Image shadow removal method based on bidirectional mapping network

A technology of bidirectional mapping and shadow removal, applied in the field of image processing, can solve problems such as color deviation of processing results, and achieve the effects of good robustness, saving the amount of neural network parameters, and high reversibility.

Pending Publication Date: 2022-08-02
UNIV OF SCI & TECH OF CHINA
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, when the current shadow removal method realizes shadow removal, there will be a certain color deviation in the processing result

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 shadow removal method based on bidirectional mapping network
  • Image shadow removal method based on bidirectional mapping network
  • Image shadow removal method based on bidirectional mapping network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] In this embodiment, as figure 1 As shown, an image shadow removal method based on bidirectional mapping network is carried out as follows:

[0049] Step 1, obtain a shadow image to be processed and its corresponding shadow mask image and shadowless image I ns And preprocess to get the preprocessed shadow image Preprocessed shadow mask image and the preprocessed shadow mask image Among them, H and W represent the height and width of the image respectively; in preprocessing, the same preprocessing process is performed on the input shadow image data and shadow mask image data, including operations such as cropping, flipping, and rotating.

[0050] preprocessed shadow image The initial colormap can be obtained Shadow image initial colormap C s is through the original image I s Divide by the mean computed along the RGB channels of the image.

[0051] Step 2, build by n 1 A convolution kernel is a 1 ×a 1 A color extraction network θ consisting of convolutional...

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 an image shadow removal method based on a bidirectional mapping network, and the method comprises the steps: 1, inputting a shadow image to be processed, constructing a color extraction network, and obtaining the color invariance information of the shadow image as the guide information of shadow removal; 2, constructing a bidirectional mapping module to realize feature extraction and feature mapping of a bidirectional mapping network; and 3, inputting the shadow image and related color guidance information into the constructed bidirectional mapping network to obtain a reconstructed shadow-free image. According to the method, the auxiliary supervision effect of shadow generation on shadow removal is fully considered, a bidirectional mapping network is constructed to remove the shadow in the image, and meanwhile, color guide information is introduced during shadow removal, so that the problem of color deviation possibly occurring during image restoration is reduced, and a better shadow removal effect can be achieved.

Description

technical field [0001] The invention belongs to the technical field of image processing, particularly relates to image shadow removal, and proposes an image shadow removal method based on a bidirectional mapping network. Background technique [0002] Shadows are caused by the occlusion of light sources by certain objects, and are common in everyday scenes. However, the degradation of the shadow phenomenon will affect the illumination and color information of the target image, which brings great challenges to other computer vision tasks, such as: target detection, target tracking, face detection, etc. Shadow removal can obtain better visual images for the human eye, and is also an important preprocessing link in these computer vision tasks. [0003] At present, methods based on neural networks have dominated the field of image shadow removal, and have achieved very good restoration results. However, the current supervision methods mainly rely on paired images to train neura...

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): G06T5/00G06V10/56G06V10/82G06N3/04G06N3/08
CPCG06V10/56G06V10/82G06N3/08G06N3/084G06N3/045G06T5/94
Inventor 查正军傅雪阳朱禹睿黄杰王洋
Owner UNIV OF SCI & TECH OF CHINA
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