Motion Blur Prior

0533761 - ÚTIA 2021 RIV US eng C - Konferenční příspěvek (zahraniční konf.)
Šroubek, Filip - Kotera, Jan
Motion Blur Prior.
2020 IEEE International Conference on Image Processing (ICIP). Piscataway: IEEE, 2020, s. 928-932. ISBN 978-1-7281-6396-3. ISSN 1522-4880. E-ISSN 2381-8549.
[2020 IEEE International Conference on Image Processing (ICIP). Abu Dhabi (AE), 25.10.2020-28.10.2020]
Grant CEP: GA ČR GA18-05360S
Institucionální podpora: RVO:67985556
Klíčová slova: deblurring * deconvolution * motion blur * atomic norm * convolutional sparse coding
Obor OECD: Computer hardware and architecture
http://library.utia.cas.cz/separaty/2020/ZOI/sroubek-0533761.pdf

We have proposed a novel methodology for generating priors that favor motion blur. Priors play an important role of regularizers in image deblurring algorithms. Image priors are frequently studied and many forms were proposed in the literature. Blur priors are considered less important and the most common forms are simple uniform distributions with domain constraints. We propose a more informative blur prior based on the notion of atomic norm which favors blurs composed of line segments and is suitable for motion blur. The prior is formulated as a linear program that can be inserted into any optimization task. Evaluation is conducted on blind deblurring of moving objects.
Trvalý link: http://hdl.handle.net/11104/0312100