Borrow it
Coverart for item
The Resource Improving extreme low-light image denoising via residual learning, Paras Maharjan

Improving extreme low-light image denoising via residual learning, Paras Maharjan

Creator
Author
Contributor
Summary
Taking a satisfactory picture in a low-light environment remains a challenging problem. Low-light imaging mainly suffers from noise due to the low signal-to-noise ratio. Many methods have been proposed for the task of image denoising, but they fail to work with the noise under extremely low light conditions. Recently, deep learning based approaches have been presented that have higher objective quality than traditional methods, but they usually have high computation cost which makes them impractical to use in real-time applications or where the computational resource is limited. In this paper, we propose a new residual learning based deep neural network for end-to-end extreme low-light image denoising that can not only significantly reduce the computational cost but also improve the performance over existing methods in both objective and subjective metrics. Specifically, in one setting we achieved 29x speedup with higher PSNR. Subjectively, our method provides better color reproduction and preserves more detailed texture information compared to state of the art methods
Language
eng
Work
Publication
Extent
1 online resource (24 pages)
Note
  • "A thesis in Electrical Engineering."
  • Advisor: Zhu Li
  • Vita
Contents
  • Introduction
  • Related work
  • Method
  • Experiments
  • Conclusion
Instance
Label
Improving extreme low-light image denoising via residual learning
Title
Improving extreme low-light image denoising via residual learning
Statement of responsibility
Paras Maharjan
Creator
Contributor
Author
Degree supervisor
Subject
Genre
Language
eng
Summary
Taking a satisfactory picture in a low-light environment remains a challenging problem. Low-light imaging mainly suffers from noise due to the low signal-to-noise ratio. Many methods have been proposed for the task of image denoising, but they fail to work with the noise under extremely low light conditions. Recently, deep learning based approaches have been presented that have higher objective quality than traditional methods, but they usually have high computation cost which makes them impractical to use in real-time applications or where the computational resource is limited. In this paper, we propose a new residual learning based deep neural network for end-to-end extreme low-light image denoising that can not only significantly reduce the computational cost but also improve the performance over existing methods in both objective and subjective metrics. Specifically, in one setting we achieved 29x speedup with higher PSNR. Subjectively, our method provides better color reproduction and preserves more detailed texture information compared to state of the art methods
Cataloging source
UMK
http://library.link/vocab/creatorDate
1991-
http://library.link/vocab/creatorName
Maharjan, Paras
Degree
M.S.
Dissertation note
(School of Computing and Engineering).
Dissertation year
2019.
Granting institution
University of Missouri-Kansas City,
Illustrations
illustrations
Index
no index present
Literary form
non fiction
Nature of contents
  • dictionaries
  • bibliography
  • theses
http://library.link/vocab/relatedWorkOrContributorName
Li, Zhu
http://library.link/vocab/subjectName
  • Image processing
  • Electronic noise
  • Available light photography
Label
Improving extreme low-light image denoising via residual learning, Paras Maharjan
Instantiates
Publication
Copyright
Note
  • "A thesis in Electrical Engineering."
  • Advisor: Zhu Li
  • Vita
Antecedent source
not applicable
Bibliography note
Includes bibliographical references (pages 21-23)
Carrier category
online resource
Carrier category code
  • cr
Carrier MARC source
rdacarrier
Color
black and white
Content category
text
Content type code
  • txt
Content type MARC source
rdacontent
Contents
Introduction -- Related work -- Method -- Experiments -- Conclusion
Control code
1135063270
Dimensions
unknown
Extent
1 online resource (24 pages)
File format
one file format
Form of item
online
Level of compression
mixed
Media category
computer
Media MARC source
rdamedia
Media type code
  • c
Other physical details
illustrations.
Quality assurance targets
not applicable
Specific material designation
remote
System control number
(OCoLC)1135063270
System details
  • The full text of the thesis is available as an Adobe Acrobat .pdf file; Adobe Acrobat Reader required to view the file
  • Mode of access: World Wide Web
Label
Improving extreme low-light image denoising via residual learning, Paras Maharjan
Publication
Copyright
Note
  • "A thesis in Electrical Engineering."
  • Advisor: Zhu Li
  • Vita
Antecedent source
not applicable
Bibliography note
Includes bibliographical references (pages 21-23)
Carrier category
online resource
Carrier category code
  • cr
Carrier MARC source
rdacarrier
Color
black and white
Content category
text
Content type code
  • txt
Content type MARC source
rdacontent
Contents
Introduction -- Related work -- Method -- Experiments -- Conclusion
Control code
1135063270
Dimensions
unknown
Extent
1 online resource (24 pages)
File format
one file format
Form of item
online
Level of compression
mixed
Media category
computer
Media MARC source
rdamedia
Media type code
  • c
Other physical details
illustrations.
Quality assurance targets
not applicable
Specific material designation
remote
System control number
(OCoLC)1135063270
System details
  • The full text of the thesis is available as an Adobe Acrobat .pdf file; Adobe Acrobat Reader required to view the file
  • Mode of access: World Wide Web

Subject

Genre

Library Locations

  • Health Sciences LibraryBorrow it
    2411 Holmes St, Kansas City, Kansas City, MO, 64108, US
    39.083418 -94.575323
  • LaBudde Special CollectionsBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.034642 -94.576835
  • Leon E. Bloch Law LibraryBorrow it
    500 E. 52nd Street, Kansas City, MO, 64110, US
    39.032488 -94.581967
  • Marr Sound ArchivesBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.034642 -94.576835
  • Miller Nichols LibraryBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.035061 -94.576518
  • UMKCBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.035061 -94.576518
  • UMKCBorrow it
    800 E 51st St, Kansas City, MO, 64110, US

Library Links

Structured data from the Bibframe namespace is licensed under the Creative Commons Attribution 4.0 International License by University of Missouri-Kansas City Libraries. Additional terms may apply to data associated with third party namespaces.
Processing Feedback ...