Enhancing the Realism of Sketch and Painted Portraits With Adaptable Patches

Simple item page
dc.contributor.authorLee, Yin‐Hsuanen_US
dc.contributor.authorChang, Yu‐Kaien_US
dc.contributor.authorChang, Yu‐Lunen_US
dc.contributor.authorLin, I‐Chenen_US
dc.contributor.authorWang, Yu‐Shuenen_US
dc.contributor.authorLin, Wen‐Chiehen_US
dc.contributor.editorChen, Min and Benes, Bedrichen_US
dc.date.accessioned2018-04-05T12:48:40Z
dc.date.available2018-04-05T12:48:40Z
dc.date.issued2018
dc.description.abstractRealizing unrealistic faces is a complicated task that requires a rich imagination and comprehension of facial structures. When face matching, warping or stitching techniques are applied, existing methods are generally incapable of capturing detailed personal characteristics, are disturbed by block boundary artefacts, or require painting‐photo pairs for training. This paper presents a data‐driven framework to enhance the realism of sketch and portrait paintings based only on photo samples. It retrieves the optimal patches of adaptable shapes and numbers according to the content of the input portrait and collected photos. These patches are then seamlessly stitched by chromatic gain and offset compensation and multi‐level blending. Experiments and user evaluations show that the proposed method is able to generate realistic and novel results for a moderately sized photo collection.Realizing unrealistic faces is a complicated task that requires a rich imagination and comprehension of facial structures. When face matching, warping or stitching techniques are applied, existing methods are generally incapable of capturing detailed personal characteristics, are disturbed by block boundary artefacts, or require painting‐photo pairs for training. This paper presents a data‐driven framework to enhance the realism of sketch and portrait paintings based only on photo samples. It retrieves the optimal patches of adaptable shapes and numbers according to the content of the input portrait and collected photos. These patches are then seamlessly stitched by chromatic gain and offset compensation and multi‐level blending.en_US
dc.description.number1
dc.description.sectionheadersArticles
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume37
dc.identifier.doi10.1111/cgf.13261
dc.identifier.issn1467-8659
dc.identifier.pages214-225
dc.identifier.urihttps://doi.org/10.1111/cgf.13261
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13261
dc.publisher© 2018 The Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectfacial modelling
dc.subjectmatting & compositing
dc.subjectI.3.3 [Computer Graphics]: Picture/Image Generation
dc.subjectI.4.3 [Image Processing and Computer Vision]: Enhancement—Registration
dc.titleEnhancing the Realism of Sketch and Painted Portraits With Adaptable Patchesen_US
Files
Collections
37-Issue 1