Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs
KAUST DepartmentVisual Computing Center (VCC)
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Computer Science Program
Online Publication Date2016-09-17
Print Publication Date2016
Permanent link to this recordhttp://hdl.handle.net/10754/622213
MetadataShow full item record
AbstractPhotographs 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. © Springer International Publishing AG 2016.
CitationXiao L, Wang J, Heidrich W, Hirsch M (2016) Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs. Lecture Notes in Computer Science: 734–749. Available: http://dx.doi.org/10.1007/978-3-319-46487-9_45.
SponsorsThis work was supported in part by Adobe and Baseline Funding of KAUST. Part of this work was done when the first author was an intern at Adobe Research. The authors thank the anonymous reviewers for helpful suggestions.