Abstract
Images taken in low-light conditions with handheld cameras are often blurry due to the required long exposure time. Although significant progress has been made recently on image deblurring, state-of-the-art approaches often fail on low-light images, as these images do not contain a sufficient number of salient features that deblurring methods rely on. On the other hand, light streaks are common phenomena in low-light images that contain rich blur information, but have not been extensively explored in previous approaches. In this work, we propose a new method that utilizes light streaks to help deblur low-light images. We introduce a non-linear blur model that explicitly models light streaks and their underlying light sources, and poses them as constraints for estimating the blur kernel in an optimization framework. Our method also automatically detects useful light streaks in the input image. Experimental results show that our approach obtains good results on challenging real-world examples that no other methods could achieve before.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
| Publisher | IEEE Computer Society |
| Pages | 3382-3389 |
| Number of pages | 8 |
| ISBN (Electronic) | 9781479951178, 9781479951178 |
| DOIs | |
| Publication status | Published - 2014 Sep 24 |
| Event | 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States Duration: 2014 Jun 23 → 2014 Jun 28 |
Publication series
| Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|---|
| ISSN (Print) | 1063-6919 |
Other
| Other | 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 |
|---|---|
| Country | United States |
| City | Columbus |
| Period | 14/6/23 → 14/6/28 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition
Cite this
}
Deblurring low-light images with light streaks. / Hu, Zhe; Cho, Sunghyun; Wang, Jue; Yang, Ming Hsuan.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014. p. 3382-3389 6909828 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Deblurring low-light images with light streaks
AU - Hu, Zhe
AU - Cho, Sunghyun
AU - Wang, Jue
AU - Yang, Ming Hsuan
PY - 2014/9/24
Y1 - 2014/9/24
N2 - Images taken in low-light conditions with handheld cameras are often blurry due to the required long exposure time. Although significant progress has been made recently on image deblurring, state-of-the-art approaches often fail on low-light images, as these images do not contain a sufficient number of salient features that deblurring methods rely on. On the other hand, light streaks are common phenomena in low-light images that contain rich blur information, but have not been extensively explored in previous approaches. In this work, we propose a new method that utilizes light streaks to help deblur low-light images. We introduce a non-linear blur model that explicitly models light streaks and their underlying light sources, and poses them as constraints for estimating the blur kernel in an optimization framework. Our method also automatically detects useful light streaks in the input image. Experimental results show that our approach obtains good results on challenging real-world examples that no other methods could achieve before.
AB - Images taken in low-light conditions with handheld cameras are often blurry due to the required long exposure time. Although significant progress has been made recently on image deblurring, state-of-the-art approaches often fail on low-light images, as these images do not contain a sufficient number of salient features that deblurring methods rely on. On the other hand, light streaks are common phenomena in low-light images that contain rich blur information, but have not been extensively explored in previous approaches. In this work, we propose a new method that utilizes light streaks to help deblur low-light images. We introduce a non-linear blur model that explicitly models light streaks and their underlying light sources, and poses them as constraints for estimating the blur kernel in an optimization framework. Our method also automatically detects useful light streaks in the input image. Experimental results show that our approach obtains good results on challenging real-world examples that no other methods could achieve before.
UR - http://www.scopus.com/inward/record.url?scp=84906341023&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84906341023&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2014.432
DO - 10.1109/CVPR.2014.432
M3 - Conference contribution
AN - SCOPUS:84906341023
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 3382
EP - 3389
BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PB - IEEE Computer Society
ER -