Single image dehazing using the change of detail prior

Abstract In this paper, we present a simple but effective image prior, change of detail (CoD) prior, to remove haze from a single input image. The CoD prior is developed based on the multiple scattering phenomenon in the propagation of light. By adopting the CoD prior in an image model, the thickness of the haze can be estimated effectively to recover a high quality, haze-free image. Our method is stable to image local regions containing objects in different depths. In addition, since the CoD prior is mostly sensitive to local details of the image rather than color and intensity, our method is able to handle both color and grayscale images. Our experiments showed that the proposed method achieved better results than several state-of-the-art methods, and it can be implemented very quickly.

[1]  Peter Shirley,et al.  A practical analytic model for daylight , 1999, SIGGRAPH.

[2]  Ko Nishino,et al.  Factorizing Scene Albedo and Depth from a Single Foggy Image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[3]  Shree K. Nayar,et al.  Contrast Restoration of Weather Degraded Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Qionghai Dai,et al.  Data-driven visibility enhancement using multi-camera system , 2010, Defense + Commercial Sensing.

[5]  Wilfried Philips,et al.  Image blur estimation based on the average cone of ratio in the wavelet domain , 2009, Electronic Imaging.

[6]  Yoav Y. Schechner,et al.  Blind Haze Separation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[7]  Jean-Philippe Tarel,et al.  Towards Fog-Free In-Vehicle Vision Systems through Contrast Restoration , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  S. Nayar,et al.  Interactive ( De ) Weathering of an Image using Physical Models ∗ , 2003 .

[9]  Jian Sun,et al.  Guided Image Filtering , 2010, ECCV.

[10]  Jean-Philippe Tarel,et al.  Fast visibility restoration from a single color or gray level image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[11]  Sabine Süsstrunk,et al.  Color image dehazing using the near-infrared , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[12]  Jing Pan,et al.  Robust probabilistic tensor analysis for time-variant collaborative filtering , 2013, Neurocomputing.

[13]  Xiaoou Tang,et al.  Single Image Haze Removal Using Dark Channel Prior , 2011 .

[14]  Shree K. Nayar,et al.  Instant dehazing of images using polarization , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[15]  Harry Shum,et al.  Gradient Profile Prior and Its Applications in Image Super-Resolution and Enhancement , 2011, IEEE Transactions on Image Processing.

[16]  Robby T. Tan,et al.  Visibility in bad weather from a single image , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Jean-Philippe Tarel,et al.  BLIND CONTRAST ENHANCEMENT ASSESSMENT BY GRADIENT RATIOING AT VISIBLE EDGES , 2011 .

[18]  Xuelong Li,et al.  Gabor-Based Region Covariance Matrices for Face Recognition , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[19]  Ke Lu,et al.  Single image dehazing with a physical model and dark channel prior , 2015, Neurocomputing.

[20]  Xuelong Li,et al.  Ranking Graph Embedding for Learning to Rerank , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[21]  Jean-Philippe Tarel,et al.  Improved visibility of road scene images under heterogeneous fog , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[22]  Dani Lischinski,et al.  Deep photo: model-based photograph enhancement and viewing , 2008, SIGGRAPH 2008.

[23]  Raanan Fattal,et al.  Single image dehazing , 2008, ACM Trans. Graph..