Automatic blur-kernel-size estimation for motion deblurring
| LEADER | caa a22 4500 | ||
|---|---|---|---|
| 001 | 605541213 | ||
| 003 | CHVBK | ||
| 005 | 20210128100915.0 | ||
| 007 | cr unu---uuuuu | ||
| 008 | 210128e20150501xx s 000 0 eng | ||
| 024 | 7 | 0 | |a 10.1007/s00371-014-0998-2 |2 doi |
| 035 | |a (NATIONALLICENCE)springer-10.1007/s00371-014-0998-2 | ||
| 245 | 0 | 0 | |a Automatic blur-kernel-size estimation for motion deblurring |h [Elektronische Daten] |c [Shaoguo Liu, Haibo Wang, Jue Wang, Sunghyun Cho, Chunhong Pan] |
| 520 | 3 | |a Existing image deblurring approaches often take the blur-kernel-size as an important manual parameter. When set improperly, this parameter can lead to significant errors in the estimated blur kernels. However, manually specifying a proper kernel size for an input image is usually a tedious trial-and-error process. In this paper, we propose a new approach for automatically estimating the underlying blur-kernel-size value that can lead to good kernel estimation. Our approach takes advantage of the autocorrelation map (automap) of image gradients that is known to reflect the motion blur information. We show that the standard automap suffers from structural edges in the image and cannot be directly used for kernel size estimation. To alleviate this problem, we develop a modified automap method that contains a directional attenuation component, which can effectively reduce the influence of structural edges, leading to more accurate and reliable kernel size estimation. Experimental results suggest that the proposed approach can help state-of-the-art deblurring algorithms achieve accurate kernel estimation without relying on manual parameter tweaking. | |
| 540 | |a Springer-Verlag Berlin Heidelberg, 2014 | ||
| 690 | 7 | |a Image deblurring |2 nationallicence | |
| 690 | 7 | |a Blur-kernel-size |2 nationallicence | |
| 690 | 7 | |a Motion blur prior |2 nationallicence | |
| 690 | 7 | |a Autocorrelation |2 nationallicence | |
| 690 | 7 | |a Directional attenuation |2 nationallicence | |
| 700 | 1 | |a Liu |D Shaoguo |u NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China |4 aut | |
| 700 | 1 | |a Wang |D Haibo |u School of Control Science and Engineering, Shandong University, Jinan, China |4 aut | |
| 700 | 1 | |a Wang |D Jue |u Adobe Research, Seattle, WA, USA |4 aut | |
| 700 | 1 | |a Cho |D Sunghyun |u Adobe Research, Seattle, WA, USA |4 aut | |
| 700 | 1 | |a Pan |D Chunhong |u NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China |4 aut | |
| 773 | 0 | |t The Visual Computer |d Springer Berlin Heidelberg |g 31/5(2015-05-01), 733-746 |x 0178-2789 |q 31:5<733 |1 2015 |2 31 |o 371 | |
| 856 | 4 | 0 | |u https://doi.org/10.1007/s00371-014-0998-2 |q text/html |z Onlinezugriff via DOI |
| 898 | |a BK010053 |b XK010053 |c XK010000 | ||
| 900 | 7 | |a Metadata rights reserved |b Springer special CC-BY-NC licence |2 nationallicence | |
| 908 | |D 1 |a research-article |2 jats | ||
| 949 | |B NATIONALLICENCE |F NATIONALLICENCE |b NL-springer | ||
| 950 | |B NATIONALLICENCE |P 856 |E 40 |u https://doi.org/10.1007/s00371-014-0998-2 |q text/html |z Onlinezugriff via DOI | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Liu |D Shaoguo |u NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Wang |D Haibo |u School of Control Science and Engineering, Shandong University, Jinan, China |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Wang |D Jue |u Adobe Research, Seattle, WA, USA |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Cho |D Sunghyun |u Adobe Research, Seattle, WA, USA |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Pan |D Chunhong |u NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China |4 aut | ||
| 950 | |B NATIONALLICENCE |P 773 |E 0- |t The Visual Computer |d Springer Berlin Heidelberg |g 31/5(2015-05-01), 733-746 |x 0178-2789 |q 31:5<733 |1 2015 |2 31 |o 371 | ||