Paper Info
Title
Image Inpainting for High-Resolution Textures using CNN Texture Synthesis.
Abstract
Deep 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.
Year
DOI
Venue
2017
10.2312/cgvc.20181212
arXiv: Computer Vision and Pattern Recognition
Field
DocType
Volume
Open problem,Pattern recognition,Convolutional neural network,Computer science,Image processing,Inpainting,Coherence (physics),Image segmentation,Artificial intelligence,Artificial neural network,Texture synthesis
Journal
abs/1712.03111
Citations 
PageRank 
References 
0
0.34
10
Authors
4
Name
Order
Citations
PageRank
Pascal Laube141.78
Michael Grunwald200.68
Matthias O. Franz363054.80
Georg Umlauf413416.86