Abstract
The detection of spatially-varying blur without having any information about the blur type is a challenging task. In this paper, we propose a novel effective approach to address this blur detection problem from a single image without requiring any knowledge about the blur type, level, or camera settings. Our approach computes blur detection maps based on a novel High-frequency multiscale Fusion and Sort Transform (HiFST) of gradient magnitudes. The evaluations of the proposed approach on a diverse set of blurry images with different blur types, levels, and contents demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods qualitatively and quantitatively.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 596-605 |
| Number of pages | 10 |
| Volume | 2017-January |
| ISBN (Electronic) | 9781538604571 |
| DOIs | |
| State | Published - Nov 6 2017 |
| Event | 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, United States Duration: Jul 21 2017 → Jul 26 2017 |
Other
| Other | 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 |
|---|---|
| Country | United States |
| City | Honolulu |
| Period | 7/21/17 → 7/26/17 |
Fingerprint
ASJC Scopus subject areas
- Signal Processing
- Computer Vision and Pattern Recognition
Cite this
Spatially-varying blur detection based on multiscale fused and sorted transform coefficients of gradient magnitudes. / Alireza Golestaneh, S.; Karam, Lina.
Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 596-605.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Spatially-varying blur detection based on multiscale fused and sorted transform coefficients of gradient magnitudes
AU - Alireza Golestaneh, S.
AU - Karam, Lina
PY - 2017/11/6
Y1 - 2017/11/6
N2 - The detection of spatially-varying blur without having any information about the blur type is a challenging task. In this paper, we propose a novel effective approach to address this blur detection problem from a single image without requiring any knowledge about the blur type, level, or camera settings. Our approach computes blur detection maps based on a novel High-frequency multiscale Fusion and Sort Transform (HiFST) of gradient magnitudes. The evaluations of the proposed approach on a diverse set of blurry images with different blur types, levels, and contents demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods qualitatively and quantitatively.
AB - The detection of spatially-varying blur without having any information about the blur type is a challenging task. In this paper, we propose a novel effective approach to address this blur detection problem from a single image without requiring any knowledge about the blur type, level, or camera settings. Our approach computes blur detection maps based on a novel High-frequency multiscale Fusion and Sort Transform (HiFST) of gradient magnitudes. The evaluations of the proposed approach on a diverse set of blurry images with different blur types, levels, and contents demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods qualitatively and quantitatively.
UR - http://www.scopus.com/inward/record.url?scp=85044527408&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044527408&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2017.71
DO - 10.1109/CVPR.2017.71
M3 - Conference contribution
AN - SCOPUS:85044527408
VL - 2017-January
SP - 596
EP - 605
BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PB - Institute of Electrical and Electronics Engineers Inc.
ER -