Image Inpainting for High-Resolution Textures using CNN Texture Synthesis

Simple item page
dc.contributor.authorLaube, Pascalen_US
dc.contributor.authorGrunwald, Michaelen_US
dc.contributor.authorFranz, Matthias O.en_US
dc.contributor.authorUmlauf, Georgen_US
dc.contributor.editor{Tam, Gary K. L. and Vidal, Francken_US
dc.date.accessioned2018-09-19T15:15:16Z
dc.date.available2018-09-19T15:15:16Z
dc.date.issued2018
dc.description.abstractDeep neural networks have been successfully applied to problems such as image segmentation, image super-resolution, coloration and image inpainting. In this work we propose the use of convolutional neural networks (CNN) for image inpainting of large regions in high-resolution textures. Due to limited computational resources processing high-resolution images with neural networks is still an open problem. Existing methods separate inpainting of global structure and the transfer of details, which leads to blurry results and loss of global coherence in the detail transfer step. Based on advances in texture synthesis using CNNs we propose patch-based image inpainting by a CNN that is able to optimize for global as well as detail texture statistics. Our method is capable of filling large inpainting regions, oftentimes exceeding the quality of comparable methods for high-resolution images. For reference patch look-up we propose to use the same summary statistics that are used in the inpainting process.en_US
dc.description.sectionheadersShort Papers
dc.description.seriesinformationComputer Graphics and Visual Computing (CGVC)
dc.identifier.doi10.2312/cgvc.20181212
dc.identifier.isbn978-3-03868-071-0
dc.identifier.pages103-107
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/cgvc20181212
dc.identifier.urihttps://doi.org/10.2312/cgvc.20181212
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectImage processing
dc.titleImage Inpainting for High-Resolution Textures using CNN Texture Synthesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
103-107.pdf
Size:
5.76 MB
Format:
Adobe Portable Document Format
Download
Collections
Computer Graphics & Visual Computing (CGVC) 2018