Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks

Ma, K; Fu, H; Liu, T; Wang, Z; Tao, D

Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks

Ma, K Fu, H Liu, T

Wang, Z Tao, D

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Image Processing, 2018, 27 (10), pp. 5155 - 5166
Issue Date:: 2018-10-01

Closed Access

	Filename	Description	Size
	08386849.pdf	Published Version	6.77 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Ma, K	en_US
dc.contributor.author	Fu, H	en_US
dc.contributor.author	Liu, T https://orcid.org/0000-0002-9640-6472	en_US
dc.contributor.author	Wang, Z	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.date.issued	2018-10-01	en_US
dc.identifier.citation	IEEE Transactions on Image Processing, 2018, 27 (10), pp. 5155 - 5166	en_US
dc.identifier.issn	1057-7149	en_US
dc.identifier.uri	http://hdl.handle.net/10453/131370
dc.description.abstract	© 1992-2012 IEEE. The human visual system excels at detecting the local blur of visual images, but the underlying mechanism is not well understood. Traditional views of blur such as the reduction in energy at high frequencies and loss of phase coherence at localized features have fundamental limitations. For example, they cannot well discriminate flat regions from blurred ones. Here, we propose that the high-level semantic information is critical in successfully identifying the local blur. Therefore, we resort to deep neural networks that are proficient at learning high-level features and propose the first end-to-end local blur mapping algorithm based on a fully convolutional network. By analyzing various architectures with different depths and design philosophies, we empirically show that the high-level features of deeper layers play a more important role than the low-level features of shallower layers in resolving challenging ambiguities for this task. We test the proposed method on a standard blur detection benchmark and demonstrate that it significantly advances the state-of-the-art (ODS F-score of 0.853). Furthermore, we explore the use of the generated blur maps in three applications, including the blur region segmentation, blur degree estimation, and blur magnification.	en_US
dc.relation.ispartof	IEEE Transactions on Image Processing	en_US
dc.relation.isbasedon	10.1109/TIP.2018.2847421	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks	en_US
dc.type	Journal Article
utslib.citation.volume	10	en_US
utslib.citation.volume	27	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	1702 Cognitive Sciences	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.issue	10	en_US
pubs.publication-status	Published	en_US
pubs.volume	27	en_US

Abstract:

© 1992-2012 IEEE. The human visual system excels at detecting the local blur of visual images, but the underlying mechanism is not well understood. Traditional views of blur such as the reduction in energy at high frequencies and loss of phase coherence at localized features have fundamental limitations. For example, they cannot well discriminate flat regions from blurred ones. Here, we propose that the high-level semantic information is critical in successfully identifying the local blur. Therefore, we resort to deep neural networks that are proficient at learning high-level features and propose the first end-to-end local blur mapping algorithm based on a fully convolutional network. By analyzing various architectures with different depths and design philosophies, we empirically show that the high-level features of deeper layers play a more important role than the low-level features of shallower layers in resolving challenging ambiguities for this task. We test the proposed method on a standard blur detection benchmark and demonstrate that it significantly advances the state-of-the-art (ODS F-score of 0.853). Furthermore, we explore the use of the generated blur maps in three applications, including the blur region segmentation, blur degree estimation, and blur magnification.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/131370