0381515 20240111140820.520121107235959.9 000342820400046 10.1007/978-3-642-33715-4_46 12 s. P cav_un_epca*0382719978-3-642-33715-40302-9743Lecture Notes in Computer Science636-647BerlinSpringer2012 blind deconvolution motion blur PSF cav_un_auth*0284209 Zhu X. US cav_un_auth*0101209 Šroubek Filip Zpracování obrazové informace Department of Image Processing ZOI ZOI UTIA-B Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0274481 Milanfar P. US pdf http://library.utia.cas.cz/separaty/2012/ZOI/sroubek-deconvolving psfs for a better motion deblurring using multiple images.pdf 2MB VG20102013064 GA MV cav_un_auth*0273814 GAP103/11/1552 GA ČR cav_un_auth*0273618 In this paper, instead of estimating the PSFs directly and only once from the observed images, we first generate a rough estimate of the PSFs using a robust multichannel deconvolution algorithm, and then “deconvolve the PSFs” to refine the outputs. Simulated and real data experiments show that this strategy works quite well for motion blurred images, producing state of the art results. cav_un_auth*0284210 ECCV12 - 12th European Conference on Computer Vision Florence 07.10.2012-13.10.2012 IT 2013 JD RVO:67985556 http://hdl.handle.net/11104/0211967 n.a. Proceedings Paper Computer Science Artificial Intelligence|Computer Science Theory Methods|Imaging Science Photographic Technology 100 0.314 16.66 0.49 Q2 Q2 2012 000342820400046 WOS pdf 2MB cav_un_epca*0382719 Computer Vision – ECCV 2012 978-3-642-33715-4 0302-9743 636 647 Berlin Springer 2012 7576 Lecture Notes in Computer Science