東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Deep Learning for Single Image Deblurring.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep Learning for Single Image Deblurring./
作者:	Xu, Boyan.
面頁冊數:	1 online resource (112 pages)
附註:	Source: Masters Abstracts International, Volume: 83-10.
Contained By:	Masters Abstracts International83-10.
標題:	Deep learning. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29051720click for full text (PQDT)
ISBN:	9798209933755

Deep Learning for Single Image Deblurring.
Xu, Boyan.

Deep Learning for Single Image Deblurring. - 1 online resource (112 pages)

Source: Masters Abstracts International, Volume: 83-10.

Thesis (M.Phil.)--The University of Manchester (United Kingdom), 2021.

Includes bibliographical references

Blind single image deblurring is a highly ill-posed problem. It often becomes even more challenging while blur is non-uniform. Since the rise of deep learning, many recent approaches are based on Convolutional Neural Networks (CNNs). These CNN-based approaches are diverse, in terms of their structures and components. However, existing methods have many disadvantages, for instance, they require intensive computation resources, and cannot restore sharp details when image blur is severe or non-uniform. In this thesis, a review the state-of-the-art methods in image restoration is firstly given, including image denoising, image dehazing, image super-resolution and image deblurring, especially of those learning based. Then various key elements and mechanisms in deblurring networks are analysed, including backbones, frameworks and conjecture that a good balance among receptive field, depth and efficiency.To achieve better performance, three networks are proposed in this research. By combining the strength of DenseNet and Inception-v4 to realize a balanced structure, a network is proposed and named as MixNet. A new network that uses dilated convolution and named DC-Deblur is also introduced as well as a Graph Convolutional Network (GCN) based method, termed as GCResNet. Further experiments in other image restoration tasks are given, in order to show the generalisation of the proposed methods. Quantitative evaluations in term of comprehensive image quality measures have been performed. Results show that the proposed MixNet, DS-Deblur, and GCResNet are able to elevate the state-of-the-art performance on end-to-end results for dynamic scene deblurring on all the benchmark datasets.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798209933755Subjects--Topical Terms:

3554982
Deep learning.
Index Terms--Genre/Form:

542853
Electronic books.

Deep Learning for Single Image Deblurring.
LDR:03049nmm a2200409K 4500 001 2362514
005 20231102121811.5
006 m o d
007 cr mn ---uuuuu
008 241011s2021 xx obm 000 0 eng d
020 $a 9798209933755
035 $a (MiAaPQ)AAI29051720
035 $a (MiAaPQ)Manchester_UKe24107d5-f4bd-4170-a185-5ec78eb13a42
035 $a AAI29051720
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Xu, Boyan. $3 3703251
245 1 0 $a Deep Learning for Single Image Deblurring.
264 0 $c 2021
300 $a 1 online resource (112 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 83-10.
500 $a Advisor: Yin, Hujun.
502 $a Thesis (M.Phil.)--The University of Manchester (United Kingdom), 2021.
504 $a Includes bibliographical references
520 $a Blind single image deblurring is a highly ill-posed problem. It often becomes even more challenging while blur is non-uniform. Since the rise of deep learning, many recent approaches are based on Convolutional Neural Networks (CNNs). These CNN-based approaches are diverse, in terms of their structures and components. However, existing methods have many disadvantages, for instance, they require intensive computation resources, and cannot restore sharp details when image blur is severe or non-uniform. In this thesis, a review the state-of-the-art methods in image restoration is firstly given, including image denoising, image dehazing, image super-resolution and image deblurring, especially of those learning based. Then various key elements and mechanisms in deblurring networks are analysed, including backbones, frameworks and conjecture that a good balance among receptive field, depth and efficiency.To achieve better performance, three networks are proposed in this research. By combining the strength of DenseNet and Inception-v4 to realize a balanced structure, a network is proposed and named as MixNet. A new network that uses dilated convolution and named DC-Deblur is also introduced as well as a Graph Convolutional Network (GCN) based method, termed as GCResNet. Further experiments in other image restoration tasks are given, in order to show the generalisation of the proposed methods. Quantitative evaluations in term of comprehensive image quality measures have been performed. Results show that the proposed MixNet, DS-Deblur, and GCResNet are able to elevate the state-of-the-art performance on end-to-end results for dynamic scene deblurring on all the benchmark datasets.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Deep learning. $3 3554982
650 4 $a Digital cameras. $3 602915
650 4 $a Wavelet transforms. $3 3681479
650 4 $a Computer peripherals. $3 659962
650 4 $a Optimization. $3 891104
650 4 $a Signal processing. $3 533904
650 4 $a Cellular telephones. $3 607843
650 4 $a Inverse problems. $3 3686950
650 4 $a Intellectual property. $3 572975
650 4 $a Neural networks. $3 677449
650 4 $a Maps. $3 544078
650 4 $a Design. $3 518875
650 4 $a Regularization methods. $3 3688999
650 4 $a Art. $3 516292
650 4 $a Algorithms. $3 536374
650 4 $a Parameter estimation. $3 567557
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
650 4 $a Electrical engineering. $3 649834
650 4 $a Engineering. $3 586835
650 4 $a Fine arts. $3 2122690
650 4 $a Mathematics. $3 515831
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0389
690 $a 0513
690 $a 0800
690 $a 0984
690 $a 0544
690 $a 0537
690 $a 0357
690 $a 0405
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a The University of Manchester (United Kingdom). $3 3422292
773 0 $t Masters Abstracts International $g 83-10.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29051720 $z click for full text (PQDT)