Show simple item record

dc.contributor.authorCho, Taeg Sang
dc.contributor.authorZitnick, C. Lawrence
dc.contributor.authorJoshi, Neel
dc.contributor.authorKang, Sing Bing
dc.contributor.authorSzeliski, Richard
dc.contributor.authorFreeman, William T.
dc.date.accessioned2012-09-10T15:04:56Z
dc.date.available2012-09-10T15:04:56Z
dc.date.issued2011-08
dc.date.submitted2011-06
dc.identifier.issn0162-8828
dc.identifier.urihttp://hdl.handle.net/1721.1/72590
dc.description.abstractThe restoration of a blurry or noisy image is commonly performed with a MAP estimator, which maximizes a posterior probability to reconstruct a clean image from a degraded image. A MAP estimator, when used with a sparse gradient image prior, reconstructs piecewise smooth images and typically removes textures that are important for visual realism. We present an alternative deconvolution method called iterative distribution reweighting (IDR) which imposes a global constraint on gradients so that a reconstructed image should have a gradient distribution similar to a reference distribution. In natural images, a reference distribution not only varies from one image to another, but also within an image depending on texture. We estimate a reference distribution directly from an input image for each texture segment. Our algorithm is able to restore rich mid-frequency textures. A large-scale user study supports the conclusion that our algorithm improves the visual realism of reconstructed images compared to those of MAP estimators.en_US
dc.language.isoen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/tpami.2011.166en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alike 3.0en_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/en_US
dc.sourceOther Repositoryen_US
dc.titleImage Restoration by Matching Gradient Distributionsen_US
dc.typeArticleen_US
dc.identifier.citationTaeg Sang Cho et al. “Image Restoration by Matching Gradient Distributions.” IEEE Transactions on Pattern Analysis and Machine Intelligence 34.4 (2012): 683–694.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.approverFreeman, William T.
dc.contributor.mitauthorFreeman, William T.
dc.relation.journalIEEE Transactions on Pattern Analysis and Machine Intelligenceen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dspace.orderedauthorsTaeg Sang Cho; Zitnick, C. L.; Joshi, N.; Sing Bing Kang, N.; Szeliski, R.; Freeman, W. T.en
dc.identifier.orcidhttps://orcid.org/0000-0002-2231-7995
mit.licenseOPEN_ACCESS_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record