Two-stage image rain removal method and system based on residual adversarial refinement network

A residual image and network technology, applied in the field of computer vision, can solve problems such as fuzzy distortion, inapplicable rain image modeling methods, and complex simulation data

Active Publication Date: 2020-05-12
EAST CHINA NORMAL UNIV +1
View PDF2 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problem that the rainwater image modeling method in the prior art is not suitable for real rainwater images, and the real rainwater images are often much more complex tha

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
  • Two-stage image rain removal method and system based on residual adversarial refinement network
  • Two-stage image rain removal method and system based on residual adversarial refinement network
  • Two-stage image rain removal method and system based on residual adversarial refinement network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0100] refer to Figure 1 to Figure 9 , this embodiment includes the following steps:

[0101] Step 1: Train the first-stage residual network to decompose the rainy image into a background image and a residual image.

[0102] Specifically, the network structure uses three convolutional layers (encoding), 12 residual modules, and three deconvolutional layers (decoding). The size of the input image in the training process is 256*256, because all convolutional neural network structures of the present invention are full convolution structures, so they are not affected by the size of the image during the test process, such as inputting a rainy image with a size of 320*240, after After the two-stage network, the input is still 320*240 in size.

[0103] Step 2: Train the second-stage adversarial refinement network to obtain the second-stage deraining results.

[0104] Specifically, the network parameters of the first stage are fixed, and the residual image output by the first stag...

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 rain removal method based on a residual adversarial refinement network, which can effectively remove raindrops in an image and restore a real scene image. According tothe method, rain removal is divided into two stages, in the first stage, a residual image is removed from an original image, a clear image is recovered, the recovered image is input into the second stage, background information of the part shielded by raindrops is recovered, the image is refined, and the quality is improved. According to the method, a rain image is regarded as synthesis of a clear image and a residual image, based on the principle, the residual image is obtained from an original rain image through a residual network, and the residual image is subtracted from the original image to obtain an output image of a first stage; in the second stage, the generative adversarial network is adopted to take the output image and the residual image in the first stage as input, the residual image is taken as an attention mechanism, and the network is assisted to recover a more real image. The invention further provides an image rain removing system.

Description

technical field [0001] The present invention relates to the technical fields of computer vision, deep learning and generative confrontational neural network, specifically a two-stage image deraining method and system based on residual confrontation refinement network, implicit rain model and its application in image processing Applications. Background technique [0002] Rain is a common weather phenomenon, but its presence may greatly affect the visibility of objects and scenes, especially in the case of heavy rain, the accumulation of rainwater from all directions makes the objects and scenes in the image become Indistinct. Images and videos captured in the rain are not only greatly affected at the level of human vision, but also for computer vision systems, it interferes and degrades the performance of many computer vision and image processing tasks, such as object detection and target tracking, Drone-based video surveillance, autonomous driving and driver assistance, an...

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): G06T5/00G06F30/27G06N3/04G06N3/08
CPCG06T5/003G06N3/08G06N3/045Y02A90/10
Inventor 邱崧黄坤耀李庆利徐伟吴思源魏茂麟孙力胡孟晗周梅刘洪英
Owner EAST CHINA NORMAL 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