Abstract
Photographs of hazy scenes typically suffer having low contrast and offer a limited visibility of the scene. This article describes a new method for single-image dehazing that relies on a generic regularity in natural images where pixels of small image patches typically exhibit a 1D distribution in RGB color space, known as color-lines. We derive a local formation model that explains the color-lines in the context of hazy scenes and use it for recovering the scene transmission based on the lines' offset from the origin. The lack of a dominant color-line inside a patch or its lack of consistency with the formation model allows us to identify and avoid false predictions. Thus, unlike existing approaches that follow their assumptions across the entire image, our algorithm validates its hypotheses and obtains more reliable estimates where possible.
In addition, we describe a Markov random field model dedicated to producing complete and regularized transmission maps given noisy and scattered estimates. Unlike traditional field models that consist of local coupling, the new model is augmented with long-range connections between pixels of similar attributes. These connections allow our algorithm to properly resolve the transmission in isolated regions where nearby pixels do not offer relevant information.
An extensive evaluation of our method over different types of images and its comparison to state-of-the-art methods over established benchmark images show a consistent improvement in the accuracy of the estimated scene transmission and recovered haze-free radiances.
Supplemental Material
- P. Carr and R. Hartley. 2009. Improved single image dehazing using geometry. In Proceedings of the Conference on Digital Image Computing: Techniques and Applications (DICTA'09). 103--110. Google ScholarDigital Library
- P. S. Chavez. 1988. An improved dark-object subtraction technique for atmonspheric scattering correction of multispectral data. Remote Sens. Environ. 24, 450--479.Google ScholarCross Ref
- Y. Du, B. Guindon, and J. Cihlar. 2002. Haze detection and removal in high resolution satellite image with wavelet analysis. IEEE Trans. Geosci. Remote Sens. 40, 1, 210--217.Google ScholarCross Ref
- R. Fattal. 2008. Single image dehazing. In ACM SIGGRAPH Papers. ACM Press, New York, 72:1--72:9. Google ScholarDigital Library
- R. Fattal. 2009. Edge-avoiding wavelets and their applications. In ACM SIGGRAPH Papers. ACM Press, New York, 22:1--22:10. Google ScholarDigital Library
- K. Gibson and T. Nguyen. 2011. On the effectiveness of the dark channel prior for single image dehazing by approximating with minimum volume ellipsoids. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'11). 1253--1256.Google Scholar
- K. Gibson and T. Nguyen. 2013a. An analysis of single image defogging methods using a color ellipsoid framework. EURASIP J. Image Video Process. 2013, 1, 37.Google ScholarCross Ref
- K. Gibson and T. Nguyen. 2013b. Fast single image fog removal using the adaptive wiener filter. In Proceedings of the International Conference on Image Processing (ICIP'13). 714--718.Google Scholar
- K. He, J. Sun, and X. Tang. 2009. Single image haze removal using dark channel prior. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09). 1956--1963.Google Scholar
- W. Hinds. 1999. Aerosol Technology: Properties, Behavior, and Measurement of Airborne Particles. Wiley-Interscience.Google Scholar
- H. Hirschmller and D. Scharstein. 2007. Evaluation of cost functions for stereo matching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'07). 1--8.Google Scholar
- J. Huang, A. Lee, and D. Mumford. 2000. Statistics of range images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'00). 324--331.Google Scholar
- J. Huang and D. Mumford. 1999. Statistics of natural images and models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'99). 637--663.Google Scholar
- C. Kim, H. Zimmer, Y. Pritch, A. Sorkine-Hornung, and M. Gross. 2013. Scene reconstruction from high spatio-angular resolution light fields. ACM Trans. Graph. 32, 4, 73:1--73:12. Google ScholarDigital Library
- J. Kopf, B. Neubert, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uyttendaele, and D. Lischinski. 2008. Deep photo: Model-based photograph enhancement and viewing. In ACM SIGGRAPH Asia Papers. ACM Press, New York, 116:1--116:10. Google ScholarDigital Library
- H. Koschmieder. 1924. Theorie der horizontalen sichtweite. Beitr. zur Phys. d. freien Atm, 171--181.Google Scholar
- L. Kratz and K. Nishino. 2009. Factorizing scene albedo and depth from a single foggy image. In Proceedings of the IEEE International Conference on Computer Vision (ICCV'09). 1701--1708.Google Scholar
- A. B. Lee, D. Mumford, and J. Huang. 2001. Occlusion models for natural images: A statistical study of a scale-invariant dead leaves model. Int. J. Comput. Vis. 41, 35--59. Google ScholarDigital Library
- A. Levin, D. Lischinski, and Y. Weiss. 2008. A closed-form solution to natural image matting. IEEE Trans. Pattern Anal. Mach. Intell. 30, 2, 228--242. Google ScholarDigital Library
- Y. Li and D. P. Huttenlocher. 2008. Sparse long-range random field and its application to image denoising. In Proceedings of the European Conference on Computer Vision (ECCV'08). Springer, 344--357. Google ScholarDigital Library
- E. Matlin and P. Milanfar. 2012. Removal of haze and noise from a single image. Proc. SPIE 8296, 82960T--82960T--12.Google Scholar
- S. Narasimhan and S. Nayar. 2000. Chromatic framework for vision in bad weather. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'00). 598--605.Google Scholar
- S. G. Narasimhan and S. K. Nayar. 2003. Interactive (de)weathering of an image using physical models. In Proceedings of the ICCV Workshop on Color and Photometric Methods in Computer Vision.Google Scholar
- S. K. Nayar and S. G. Narasimhan. 1999. Vision in bad weather. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'99). 820.Google Scholar
- K. Nishino, L. Kratz, and S. Lombardi. 2012. Bayesian defogging. Int. J. Comput. Vis. 98, 3, 263--278. Google ScholarDigital Library
- J. P. Oakley and H. Bu. 2007. Correction of simple contrast loss in color images. IEEE Trans. Image Process. 16, 2, 511--522. Google ScholarDigital Library
- I. Omer and M. Werman. 2004. Color lines: Image specific color representation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'04). 946--953. Google ScholarDigital Library
- S. Roth and M. J. Black. 2007. On the spatial statistics of optical flow. Int. J. Comput. Vis. 74, 1, 33--50. Google ScholarDigital Library
- D. Scharstein and R. Szeliski. 2002. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vis. 47, 1--3, 7--42. Google ScholarDigital Library
- Y. Schechner, S. G. Narasimhan, and S. K. Nayar. 2001. Instant dehazing of images using polarization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'01). 325--332.Google Scholar
- S. Shwartz, E. Y. Y. Namer, and Schechner. 2006. Blind haze separation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'06). 1984--1991. Google ScholarDigital Library
- K. Tan and J. P. Oakley. 2000. Enhancement of color images in poor visibility conditions. In Proceedings of the International Conference on Image Processing (ICIP'00). Vol. 2, 788--791.Google Scholar
- R. T. Tan. 2008. Visibility in bad weather from a single image. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'08). 1--8.Google ScholarCross Ref
- J.-P. Tarel and N. Hautiere. 2009. Fast visibility restoration from a single color or gray level image. In Proceedings of the IEEE International Conference on Computer Vision (ICCV'09). 2201--2208.Google Scholar
- G. Zhang, J. Jia, T.-T. Wong, and H. Bao. 2009. Consistent depth maps recovery from a video sequence. IEEE Trans. Pattern Anal. Mach. Intell. 31, 6, 974--988. Google ScholarDigital Library
- Y. Zhang, B. Guindon, and J. Cihlar. 2002. An image transform to characterize and compensate for spatial variations in thin cloud contamination of landsat images. Remote Sens. Environ. 82, 173--187.Google ScholarCross Ref
Index Terms
- Dehazing Using Color-Lines
Recommendations
Detail Recovery and Color Enhancement for Single Image Dehazing
ICNCC '22: Proceedings of the 2022 11th International Conference on Networks, Communication and ComputingDue to the complexity of taking photos on foggy days, images captured in the real world are prone to problems of detail loss, color dimness, and low saturation. Considering image dehazing as a problem of detail recovery and color enhancement, a two-...
Optimized contrast enhancement for real-time image and video dehazing
A fast and optimized dehazing algorithm for hazy images and videos is proposed in this work. Based on the observation that a hazy image exhibits low contrast in general, we restore the hazy image by enhancing its contrast. However, the overcompensation ...
Evaluating Single Image Dehazing Methods Under Realistic Sunlight Haze
Advances in Visual ComputingAbstractHaze can degrade the visibility and the image quality drastically, thus degrading the performance of computer vision tasks such as object detection. Single image dehazing is a challenging and ill-posed problem, despite being widely studied. Most ...
Comments