Deblurring Low-Light Images with Light Streaks

Zhe Hu, Sunghyun Cho, Jue Wang, Ming Hsuan Yang

Research output: Contribution to journalArticlepeer-review

20 Citations (Scopus)


Images acquired in low-light conditions with handheld cameras are often blurry, so steady poses and long exposure time are required to alleviate this problem. Although significant advances have been made in image deblurring, state-of-the-art approaches often fail on low-light images, as a sufficient number of salient features cannot be extracted for blur kernel estimation. On the other hand, light streaks are common phenomena in low-light images that have not been extensively explored in existing approaches. In this work, we propose an algorithm that utilizes light streaks to facilitate deblurring low-light images. The light streaks, which commonly exist in the low-light blurry images, contain rich information regarding camera motion and blur kernels. A method is developed in this work to detect light streaks for kernel estimation. We introduce a non-linear blur model that explicitly takes light streaks and corresponding light sources into account, and pose them as constraints for estimating the blur kernel in an optimization framework. For practical applications, the proposed algorithm is extended to handle images undergoing non-uniform blur. Experimental results show that the proposed algorithm performs favorably against the state-of-the-art methods on deblurring real-world low-light images.

Original languageEnglish
Article number8094022
Pages (from-to)2329-2341
Number of pages13
JournalIEEE transactions on pattern analysis and machine intelligence
Issue number10
Publication statusPublished - 2018 Oct 1

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Deblurring Low-Light Images with Light Streaks'. Together they form a unique fingerprint.

Cite this