Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107164
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Electrical and Electronic Engineering | en_US |
dc.creator | Xiao, J | en_US |
dc.creator | Zhao, R | en_US |
dc.creator | Lai, SC | en_US |
dc.creator | Jia, W | en_US |
dc.creator | Lam, KM | en_US |
dc.date.accessioned | 2024-06-13T01:04:19Z | - |
dc.date.available | 2024-06-13T01:04:19Z | - |
dc.identifier.isbn | 978-1-5386-6249-6 (Electronic) | en_US |
dc.identifier.isbn | 978-1-5386-6250-2 (Print on Demand(PoD)) | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/107164 | - |
dc.description | 2019 IEEE International Conference on Image Processing (ICIP), 22-25 September 2019, Taipei, Taiwan | en_US |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.rights | ©2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | en_US |
dc.rights | The following publication J. Xiao, R. Zhao, S. -C. Lai, W. Jia and K. -M. Lam, "Deep Progressive Convolutional Neural Network for Blind Super-Resolution With Multiple Degradations," 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 2019, pp. 2856-2860 is available at https://doi.org/10.1109/ICIP.2019.8803251. | en_US |
dc.subject | Blind super-resolution | en_US |
dc.subject | Deep progressive network | en_US |
dc.title | Deep progressive convolutional neural network for blind super-resolution with multiple degradations | en_US |
dc.type | Conference Paper | en_US |
dc.identifier.spage | 2856 | en_US |
dc.identifier.epage | 2860 | en_US |
dc.identifier.doi | 10.1109/ICIP.2019.8803251 | en_US |
dcterms.abstract | Blind super-resolution (SR) of blurry and noisy low-resolution (LR) images is still a challenging problem in single image super-resolution (SISR). The performance of most existing convolutional neural network (CNN)-based models is inevitably degraded when LR images are corrupted by both blur and noise. For those blind SR methods based on kernel estimation, accurate estimation is barely attained under complex degradations and this gives rise to poor-quality results. To address these problems, we propose a deep progressive network under a probabilistic framework and a novel up-sampling method for blind super-resolution with multiple degradations, which effectively utilizes image priors across scales. Experimental results show that the proposed method achieves promising performance on images with multiple degradations. | en_US |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | In Proceedings of 2019 IEEE International Conference on Image Processing (ICIP), 22-25 September 2019, Taipei, Taiwan, p. 2856-2860 | en_US |
dcterms.issued | 2019 | - |
dc.identifier.scopus | 2-s2.0-85076816442 | - |
dc.relation.conference | IEEE International Conference on Image Processing [ICIP] | en_US |
dc.description.validate | 202404 bckw | en_US |
dc.description.oa | Accepted Manuscript | en_US |
dc.identifier.FolderNumber | EIE-0321 | - |
dc.description.fundingSource | Self-funded | en_US |
dc.description.pubStatus | Published | en_US |
dc.identifier.OPUS | 20082144 | - |
dc.description.oaCategory | Green (AAM) | en_US |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Xiao_Deep_Progressive_Convolutional.pdf | Pre-Published version | 3.18 MB | Adobe PDF | View/Open |
Page views
1
Citations as of Jun 30, 2024
SCOPUSTM
Citations
12
Citations as of Jun 21, 2024
WEB OF SCIENCETM
Citations
11
Citations as of Jun 27, 2024
![](/image/google_scholar.jpg)
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.