國立虎尾科技大學 |

Single Image Super Resolution: Perceptual quality & Test-time Optimization.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Single Image Super Resolution: Perceptual quality & Test-time Optimization./
作者:	Chen, Lei.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
面頁冊數:	49 p.
附註:	Source: Masters Abstracts International, Volume: 81-02.
Contained By:	Masters Abstracts International81-02.
標題:	Computer engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13810042
ISBN:	9781085595377

Single Image Super Resolution: Perceptual quality & Test-time Optimization.
Chen, Lei.

Single Image Super Resolution: Perceptual quality & Test-time Optimization. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 49 p.

Source: Masters Abstracts International, Volume: 81-02.

Thesis (M.S.)--Duke University, 2019.

This item is not available from ProQuest Dissertations & Theses.

Image super resolution is defined as recovering a high-resolution image given a low-resolution image input. It has a wide area of applications in modern digital image processing, producing better results in areas including satellite image processing, medical image processing, microscopy image processing, astrological studies and surveillance area. However, image super resolution is an ill-posed question since there exists non-deterministic answer in the high resolution image space, making it difficult to find the optimal solution.In this work, various research directions in the area of single image super resolution are thoroughly studied. Each of the proposed methods' achievements as well as limitations including computational efficiency, perceptual performance limits are compared. The main contribution in this work including implementing a perceptual score predictor and integrating as part of the objective function in the upsampler algorithm. Apart from that, a test-time optimization algorithm is proposed, aiming at further enhance the image quality for the obtained super-resolution image from any upsampler. The proposed methods are implemented and tested using Pytorch. Results are compared on baseline applied datasets including Set5, Set14, Urban100 and DIV2K.Results from perceptual score predictor was evaluated on both PSNR precision index and Fper perceptual index, which is a combination of perceptual evaluation Ma score and NIQE score. With new objective function, the upsampler achieved to move along the trade-off curve of precision and perception. The test-time optimization algorithm achieved slightly improvements in both precision and perception index. Note that the proposed test time optimization does not require training of new neural network, thus, is computationally efficient.

ISBN: 9781085595377Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Computer Vision

Single Image Super Resolution: Perceptual quality & Test-time Optimization.
LDR:03039nam a2200385 4500 001 951817
005 20200821052201.5
008 200914s2019 ||||||||||||||||| ||eng d
020 $a 9781085595377
035 $a (MiAaPQ)AAI13810042
035 $a AAI13810042
040 $a MiAaPQ $c MiAaPQ
100 1 $a Chen, Lei. $3 793351
245 1 0 $a Single Image Super Resolution: Perceptual quality & Test-time Optimization.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 49 p.
500 $a Source: Masters Abstracts International, Volume: 81-02.
500 $a Advisor: Rudin, Cynthia.
502 $a Thesis (M.S.)--Duke University, 2019.
506 $a This item is not available from ProQuest Dissertations & Theses.
506 $a This item must not be sold to any third party vendors.
520 $a Image super resolution is defined as recovering a high-resolution image given a low-resolution image input. It has a wide area of applications in modern digital image processing, producing better results in areas including satellite image processing, medical image processing, microscopy image processing, astrological studies and surveillance area. However, image super resolution is an ill-posed question since there exists non-deterministic answer in the high resolution image space, making it difficult to find the optimal solution.In this work, various research directions in the area of single image super resolution are thoroughly studied. Each of the proposed methods' achievements as well as limitations including computational efficiency, perceptual performance limits are compared. The main contribution in this work including implementing a perceptual score predictor and integrating as part of the objective function in the upsampler algorithm. Apart from that, a test-time optimization algorithm is proposed, aiming at further enhance the image quality for the obtained super-resolution image from any upsampler. The proposed methods are implemented and tested using Pytorch. Results are compared on baseline applied datasets including Set5, Set14, Urban100 and DIV2K.Results from perceptual score predictor was evaluated on both PSNR precision index and Fper perceptual index, which is a combination of perceptual evaluation Ma score and NIQE score. With new objective function, the upsampler achieved to move along the trade-off curve of precision and perception. The test-time optimization algorithm achieved slightly improvements in both precision and perception index. Note that the proposed test time optimization does not require training of new neural network, thus, is computationally efficient.
590 $a School code: 0066.
650 4 $a Computer engineering. $3 569006
650 4 $a Information technology. $3 559429
653 $a Computer Vision
653 $a Deep Neural Networks
653 $a Objective Function
653 $a Perceptual Quality
653 $a Pixel Shift
653 $a Super Resolution
690 $a 0464
690 $a 0489
710 2 $a Duke University. $b Electrical and Computer Engineering. $3 845695
773 0 $t Masters Abstracts International $g 81-02.
790 $a 0066
791 $a M.S.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13810042