DehazeNet: An End-to-End System for Single Image Haze Removal

Single image haze removal is a challenging ill-posed problem. Existing methods use various constraints/priors to get plausible dehazing solutions. The key to achieve haze removal is to estimate a medium transmission map for an input hazy image. In this paper, we propose a trainable end-to-end system called DehazeNet, for medium transmission estimation. DehazeNet takes a hazy image as input, and outputs its medium transmission map that is subsequently used to recover a haze-free image via atmospheric scattering model. DehazeNet adopts convolutional neural network-based deep architecture, whose layers are specially designed to embody the established assumptions/priors in image dehazing. Specifically, the layers of Maxout units are used for feature extraction, which can generate almost all haze-relevant features. We also propose a novel nonlinear activation function in DehazeNet, called bilateral rectified linear unit, which is able to improve the quality of recovered haze-free image. We establish connections between the components of the proposed DehazeNet and those used in existing methods. Experiments on benchmark images show that DehazeNet achieves superior performance over existing methods, yet keeps efficient and easy to use.

[1]  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.

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

[3]  Ketan Tang,et al.  Investigating Haze-Relevant Features in a Learning Framework for Image Dehazing , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  J. E. McDonald.  The Saturation Adjustment in Numerical Modelling of Fog , 1963 .

[5]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[7]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[8]  Zhiyuan Xu,et al.  Fog Removal from Color Images using Contrast Limited Adaptive Histogram Equalization , 2009, 2009 2nd International Congress on Image and Signal Processing.

[9]  Michael Werman,et al.  Automatic recovery of the atmospheric light in hazy images , 2014, 2014 IEEE International Conference on Computational Photography (ICCP).

[10]  Wilson S. Geisler,et al.  Image quality assessment based on a degradation model , 2000, IEEE Trans. Image Process..

[11]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[12]  Richard Szeliski,et al.  High-accuracy stereo depth maps using structured light , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

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

[14]  Ko Nishino,et al.  Bayesian Defogging , 2012, International Journal of Computer Vision.

[15]  Dapeng Li,et al.  Physics-based fast single image fog removal , 2010, IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS.

[16]  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.

[17]  Gaofeng Meng,et al.  Efficient Image Dehazing with Boundary Constraint and Contextual Regularization , 2013, 2013 IEEE International Conference on Computer Vision.

[18]  Dahua Lin,et al.  Adjustable Bounded Rectifiers: Towards Deep Binary Representations , 2015, ArXiv.

[19]  Ling Shao,et al.  A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior , 2015, IEEE Transactions on Image Processing.

[20]  B. Scholkopf,et al.  Fisher discriminant analysis with kernels , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

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

[22]  Tomaso Poggio,et al.  Intracellular measurements of spatial integration and the MAX operation in complex cells of the cat primary visual cortex. , 2004, Journal of neurophysiology.

[23]  Bernhard Schölkopf,et al.  A Machine Learning Approach for Non-blind Image Deconvolution , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Yoshua Bengio,et al.  Maxout Networks , 2013, ICML.

[25]  Joonki Paik,et al.  Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering , 1998 .

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

[27]  Dani Lischinski,et al.  A Closed-Form Solution to Natural Image Matting , 2008 .

[28]  A. Cantor.  Optics of the atmosphere--Scattering by molecules and particles , 1978, IEEE Journal of Quantum Electronics.

[29]  Shree K. Nayar,et al.  Vision in bad weather , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[30]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[31]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  David J. Sakrison,et al.  The effects of a visual fidelity criterion of the encoding of images , 1974, IEEE Trans. Inf. Theory.

[33]  Truong Q. Nguyen,et al.  An Investigation of Dehazing Effects on Image and Video Coding , 2012, IEEE Transactions on Image Processing.

[34]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[35]  Rob Fergus,et al.  Restoring an Image Taken through a Window Covered with Dirt or Rain , 2013, 2013 IEEE International Conference on Computer Vision.

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

[37]  Dacheng Tao,et al.  Robust Face Recognition via Multimodal Deep Face Representation , 2015, IEEE Transactions on Multimedia.

[38]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[39]  Cosmin Ancuti,et al.  A Fast Semi-inverse Approach to Detect and Remove the Haze from a Single Image , 2010, ACCV.

[40]  Jiwen Lu,et al.  PCANet: A Simple Deep Learning Baseline for Image Classification? , 2014, IEEE Transactions on Image Processing.

[41]  Christopher Joseph Pal,et al.  Learning Conditional Random Fields for Stereo , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[42]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[43]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[45]  J. Alex Stark,et al.  Adaptive image contrast enhancement using generalizations of histogram equalization , 2000, IEEE Trans. Image Process..

[46]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[47]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[48]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[49]  Di Wu,et al.  Back propagation neural network dehazing , 2014, 2014 IEEE International Conference on Robotics and Biomimetics (ROBIO 2014).