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

Multi-level image restoration method based on partial-to-overall attention mechanism

A repair method and attention technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of ignoring the internal semantic continuity of the region, unreasonable repair results, etc.

Pending Publication Date: 2020-05-08
FUDAN UNIV
View PDF4 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method pays too much attention to the utilization of existing information and ignores the semantic continuity inside missing regions, thus may produce visually unreasonable inpainting results

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
  • Multi-level image restoration method based on partial-to-overall attention mechanism
  • Multi-level image restoration method based on partial-to-overall attention mechanism
  • Multi-level image restoration method based on partial-to-overall attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The embodiments of the present invention will be described in detail below, but the protection scope of the present invention is not limited to the examples.

[0049] use figure 1 The network structure shown, with the dataset Paris StreetView [5] (Paris street view data set, including a total of 14,900 training pictures and 100 test pictures) to train the network to obtain an image restoration model.

[0050] The specific steps are:

[0051] (1) Before training, initialize the network parameters randomly, and uniformly adjust the image size in the training set to 610×350;

[0052] (2) During training, the image size is randomly cropped to 256×256, and normalized to the [0,1] interval. The Adam optimizer is used to update the model parameters, the initial learning rate of the generator is 0.0001, and the learning rate of the discriminator is one-tenth of the generator. Minimize the loss function using mini-batch stochastic gradient descent. The batch size is set to ...

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 digital image intelligent processing, and particularly relates to a multi-level image restoration method based on a partial-to-overall attention mechanism. Image restoration refers to replacing and generating lost or defective image data by using an algorithm. The method comprises the steps that a multi-level deep convolutional neural network generator structure is provided; and an attention mechanism convolution layer from is partially and wholly integrated into a generator and a discriminator of the network. An image block discriminator and four loss functions of reconstruction loss, perception loss, style loss and adversarial loss are introduced in the training process of the network to assist a generator to learn an image restoration task. Experimental results show that the restored image with vivid details and a reasonable overall structure can be generated, and the image restoration problem is effectively solved.

Description

technical field [0001] The invention belongs to the technical field of digital image intelligent processing, and relates to an image restoration method, more specifically, to a multi-level image restoration method based on a part-to-whole attention mechanism. Background technique [0002] As the media people use to store information has changed, so has the definition of the task of image restoration, from the restoration of damaged frescoes during the Renaissance to the restoration of aging paper photographs in earlier years , and then to the current processing of digital pictures stored on the computer. It should be emphasized that the application of image repair is not limited to the function of "repair". In addition, the current repair technology can also be applied to object removal, watermark removal, occlusion removal, face acne removal, skin smoothing, etc. Scenes. [0003] Early image inpainting techniques are mainly divided into two categories based on the size of...

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): G06T5/00G06N3/04G06N3/08
CPCG06N3/08G06T2207/20081G06N3/045G06T5/77Y02T10/40
Inventor 颜波陈鹤丹
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