Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs

L. Xiao, J. Wang, W. Heidrich, M. Hirsch
Computer Vision ECCV 2016, Volume 9907 of the series Lecture Notes in Computer Science, pp. 734-749, (2016)

Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs

Keywords

Text document, Camera motion, Blind deblurring, High-order filters

Abstract

​Photographs of text documents taken by hand-held cameras can be easily degraded by camera motion during exposure. In this paper, we propose a new method for blind deconvolution of document images. Observing that document images are usually dominated by small-scale high-order structures, we propose to learn a multi-scale, interleaved cascade of shrinkage fields model, which contains a series of high-order filters to facilitate joint recovery of blur kernel and latent image. With extensive experiments, we show that our method produces high quality results and is highly efficient at the same time, making it a practical choice for deblurring high resolution text images captured by modern mobile devices.

Code

DOI: 10.1007/978-3-319-46487-9_45

Sources

Website PDF

See all publications 2016