File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A Benchmark for Edge-Preserving Image Smoothing

TitleA Benchmark for Edge-Preserving Image Smoothing
Authors
KeywordsSmoothing methods
Image edge detection
Benchmark testing
Neural networks
Image reconstruction
Issue Date2019
PublisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83
Citation
IEEE Transactions on Image Processing, 2019, v. 28, p. 3556-3570 How to Cite?
AbstractEdge-preserving image smoothing is an important step for many low-level vision problems. Though many algorithms have been proposed, there are several difficulties hindering its further development. First, most existing algorithms cannot perform well on a wide range of image contents using a single parameter setting. Second, the performance evaluation of edge-preserving image smoothing remains subjective, and there is a lack of widely accepted datasets to objectively compare the different algorithms. To address these issues and further advance the state of the art, in this paper, we propose a benchmark for edge-preserving image smoothing. This benchmark includes an image dataset with ground truth image smoothing results as well as baseline algorithms that can generate competitive edge-preserving smoothing results for a wide range of image contents. The established dataset contains 500 training and testing images with a number of representative visual object categories, while the baseline methods in our benchmark are built upon representative deep convolutional network architectures, on top of which we design novel loss functions well suited for the edge-preserving image smoothing. The trained deep networks run faster than most of the state-of-the-art smoothing algorithms with leading smoothing results both qualitatively and quantitatively. The benchmark will be made publicly accessible.
Persistent Identifierhttp://hdl.handle.net/10722/271349
ISSN
2023 Impact Factor: 10.8
2023 SCImago Journal Rankings: 3.556
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZHU, F-
dc.contributor.authorLIANG, Z-
dc.contributor.authorJIA, X-
dc.contributor.authorZHANG, L-
dc.contributor.authorYu, Y-
dc.date.accessioned2019-06-24T01:08:09Z-
dc.date.available2019-06-24T01:08:09Z-
dc.date.issued2019-
dc.identifier.citationIEEE Transactions on Image Processing, 2019, v. 28, p. 3556-3570-
dc.identifier.issn1057-7149-
dc.identifier.urihttp://hdl.handle.net/10722/271349-
dc.description.abstractEdge-preserving image smoothing is an important step for many low-level vision problems. Though many algorithms have been proposed, there are several difficulties hindering its further development. First, most existing algorithms cannot perform well on a wide range of image contents using a single parameter setting. Second, the performance evaluation of edge-preserving image smoothing remains subjective, and there is a lack of widely accepted datasets to objectively compare the different algorithms. To address these issues and further advance the state of the art, in this paper, we propose a benchmark for edge-preserving image smoothing. This benchmark includes an image dataset with ground truth image smoothing results as well as baseline algorithms that can generate competitive edge-preserving smoothing results for a wide range of image contents. The established dataset contains 500 training and testing images with a number of representative visual object categories, while the baseline methods in our benchmark are built upon representative deep convolutional network architectures, on top of which we design novel loss functions well suited for the edge-preserving image smoothing. The trained deep networks run faster than most of the state-of-the-art smoothing algorithms with leading smoothing results both qualitatively and quantitatively. The benchmark will be made publicly accessible.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83-
dc.relation.ispartofIEEE Transactions on Image Processing-
dc.rightsIEEE Transactions on Image Processing. Copyright © Institute of Electrical and Electronics Engineers.-
dc.rights©20xx 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.-
dc.subjectSmoothing methods-
dc.subjectImage edge detection-
dc.subjectBenchmark testing-
dc.subjectNeural networks-
dc.subjectImage reconstruction-
dc.titleA Benchmark for Edge-Preserving Image Smoothing-
dc.typeArticle-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TIP.2019.2908778-
dc.identifier.scopuseid_2-s2.0-85067251164-
dc.identifier.hkuros298092-
dc.identifier.volume28-
dc.identifier.spage3556-
dc.identifier.epage3570-
dc.identifier.isiWOS:000471067800002-
dc.publisher.placeUnited States-
dc.identifier.issnl1057-7149-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats