S. Krajči (ed.): ITAT 2018 Proceedings, p. 43
CEUR Workshop Proceedings Vol. 2203, ISSN 1613-0073, c 2018 Filip Šroubek



                              Digital image restoration: blur as a motion cue

                                                           Filip Šroubek

                                                               AVČR

     Abstract: We rely on images with ever growing empha-
     sis. Our perception of the world is however limited by im-
     perfect measuring conditions and devices used to acquire
     images. By image restoration, we understand mathemati-
     cal procedures removing degradation from images. Two
     prominent topics of image restoration that has evolved
     considerably in the last 10 years are blind deconvolution
     and superresolution. Deconvolution by itself is an ill-
     posed inverse problem and one of the fundamental topics
     of image processing. The blind case, when the blur kernel
     is also unknown, is even more challenging and requires
     special optimization approaches to converge to the correct
     solution. Superresolution extends blind deconvolution by
     recovering lost spatial resolution of images.
        In this talk we will cover the recent advances in both
     topics that pave the way from theory to practice. Various         Filip Šroubek is currently with the Institute of Infor-
     real acquisition scenarios will be discussed together with     mation Theory and Automation, the Czech Academy of
     proposed solutions for both blind deconvolution and su-        Sciences, and lectures at Charles University. From 2004
     perresolution and efficient numerical optimization meth-       to 2006, he was on a postdoctoral position in the Insti-
     ods, which allow fast implementation. Finally we will          tuto de Optica, CSIC, Madrid, Spain. In 2010 and 2011,
     illustrate that combing deblurring with tracking leads to      he was the Fulbright Visiting Scholar at the University of
     interesting applications in videos.                            California, Santa Cruz. His research covers all aspects of
                                                                    image processing, in particular, image restoration (denois-
                                                                    ing, blind deconvolution, super-resolution) and image fu-
                                                                    sion (multimodal, multifocus). He is an author of 8 book
                                                                    chapters and over 60 journal and conference papers.