File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: An L1 image transform for edge-preserving smoothing and scene-level intrinsic decomposition

TitleAn L1 image transform for edge-preserving smoothing and scene-level intrinsic decomposition
Authors
Issue Date2015
PublisherAssociation for Computing Machinery, Inc. The Journal's web site is located at http://tog.acm.org
Citation
ACM Transactions on Graphics, 2015, v. 34 n. 4, article no. 78 How to Cite?
AbstractIdentifying sparse salient structures from dense pixels is a longstanding problem in visual computing. Solutions to this problem can benefit both image manipulation and understanding. In this paper, we introduce an image transform based on the L1 norm for piecewise image flattening. This transform can effectively preserve and sharpen salient edges and contours while eliminating insignificant details, producing a nearly piecewise constant image with sparse structures. A variant of this image transform can perform edge-preserving smoothing more effectively than existing state-of-the-art algorithms. We further present a new method for complex scene-level intrinsic image decomposition. Our method relies on the above image transform to suppress surface shading variations, and perform probabilistic reflectance clustering on the flattened image instead of the original input image to achieve higher accuracy. Extensive testing on the Intrinsic-Images-in-the-Wild database indicates our method can perform significantly better than existing techniques both visually and numerically. The obtained intrinsic images have been successfully used in two applications, surface retexturing and 3D object compositing in photographs.
Persistent Identifierhttp://hdl.handle.net/10722/215521
ISSN
2015 Impact Factor: 4.218
2015 SCImago Journal Rankings: 2.552

 

DC FieldValueLanguage
dc.contributor.authorBi, S-
dc.contributor.authorHan, X-
dc.contributor.authorYu, Y-
dc.date.accessioned2015-08-21T13:28:50Z-
dc.date.available2015-08-21T13:28:50Z-
dc.date.issued2015-
dc.identifier.citationACM Transactions on Graphics, 2015, v. 34 n. 4, article no. 78-
dc.identifier.issn0730-0301-
dc.identifier.urihttp://hdl.handle.net/10722/215521-
dc.description.abstractIdentifying sparse salient structures from dense pixels is a longstanding problem in visual computing. Solutions to this problem can benefit both image manipulation and understanding. In this paper, we introduce an image transform based on the L1 norm for piecewise image flattening. This transform can effectively preserve and sharpen salient edges and contours while eliminating insignificant details, producing a nearly piecewise constant image with sparse structures. A variant of this image transform can perform edge-preserving smoothing more effectively than existing state-of-the-art algorithms. We further present a new method for complex scene-level intrinsic image decomposition. Our method relies on the above image transform to suppress surface shading variations, and perform probabilistic reflectance clustering on the flattened image instead of the original input image to achieve higher accuracy. Extensive testing on the Intrinsic-Images-in-the-Wild database indicates our method can perform significantly better than existing techniques both visually and numerically. The obtained intrinsic images have been successfully used in two applications, surface retexturing and 3D object compositing in photographs.-
dc.languageeng-
dc.publisherAssociation for Computing Machinery, Inc. The Journal's web site is located at http://tog.acm.org-
dc.relation.ispartofACM Transactions on Graphics-
dc.rightsACM Transactions on Graphics. Copyright © Association for Computing Machinery, Inc.-
dc.rights©ACM, 2015. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM Transactions on Graphics, 2015, v. 34 n. 4, article no. 78. http://doi.acm.org/10.1145/2766946-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.titleAn L1 image transform for edge-preserving smoothing and scene-level intrinsic decomposition-
dc.typeArticle-
dc.identifier.emailBi, S: bisai@hku.hk-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.description.naturepostprint-
dc.identifier.doi10.1145/2766946-
dc.identifier.hkuros249502-
dc.identifier.volume34-
dc.identifier.issue4-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats