Deblurring Low-light Images with Light Streaks

Zhe Hu§      Sunghyun Cho      Jue Wang      Ming-Hsuan Yang§

§UC Merced       Adobe

IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014)


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 realworld examples that no other methods could achieve before.

Paper and MATLAB code

The paper and MATLAB code can be found here. [PDF] [Poster] [MATLAB code] [Test data]


title = {Deblurring Low-light Images with Light Streaks},
author = {Zhe Hu, Sunghyun Cho, Jue Wang and Ming-Hsuan Yang},
journal = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014)},
year = {2014}