Intrinsic Image Decomposition Using Multi‐Scale Measurements and Sparsity

dc.contributor.authorDing, Shouhongen_US
dc.contributor.authorSheng, Binen_US
dc.contributor.authorHou, Xiaonanen_US
dc.contributor.authorXie, Zhifengen_US
dc.contributor.authorMa, Lizhuangen_US
dc.contributor.editorChen, Min and Zhang, Hao (Richard)en_US
dc.date.accessioned2018-01-10T07:36:25Z
dc.date.available2018-01-10T07:36:25Z
dc.date.issued2017
dc.description.abstractAutomatic decomposition of intrinsic images, especially for complex real‐world images, is a challenging under‐constrained problem. Thus, we propose a new algorithm that generates and combines multi‐scale properties of chromaticity differences and intensity contrast. The key observation is that the estimation of image reflectance, which is neither a pixel‐based nor a region‐based property, can be improved by using multi‐scale measurements of image content. The new algorithm iteratively coarsens a graph reflecting the reflectance similarity between neighbouring pixels. Then multi‐scale reflectance properties are aggregated so that the graph reflects the reflectance property at different scales. This is followed by a sparse regularization on the whole reflectance image, which enforces the variation in reflectance images to be high‐frequency and sparse. We formulate this problem through energy minimization which can be solved efficiently within a few iterations. The effectiveness of the new algorithm is tested with the Massachusetts Institute of Technology (MIT) dataset, the Intrinsic Images in the Wild (IIW) dataset, and various natural images.Automatic decomposition of intrinsic images, especially for complex real‐world images, is a challenging under‐constrained problem. Thus, we propose a new algorithm that generates and combines multi‐scale properties of chromaticity differences and intensity contrast. The key observation is that the estimation of image reflectance, which is neither a pixel‐based nor a region‐based property, can be improved by using multi‐scale measurements of image content. The new algorithm iteratively coarsens a graph reflecting the reflectance similarity between neighbouring pixels.en_US
dc.description.number6
dc.description.sectionheadersArticles
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume36
dc.identifier.doi10.1111/cgf.12874
dc.identifier.issn1467-8659
dc.identifier.pages251-261
dc.identifier.urihttps://doi.org/10.1111/cgf.12874
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf12874
dc.publisher© 2017 The Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectintrinsic image
dc.subjectmultiscale measurements
dc.subjectsparsity
dc.subjectI.3.3 [Computer Graphics]: Picture/Image Generation–Line and curve generation
dc.titleIntrinsic Image Decomposition Using Multi‐Scale Measurements and Sparsityen_US
Files
Collections