Abstract
Recently, data-driven approaches are prevailing in low-level image processing including single image dehazing. The performance of these methods can behave better when the learning process adapts to the input. This input-adaptive training demands efficiently selecting optimal examples for the input from a large training set. In this paper, we address the issue of input-specific example searching and propose a fast searching strategy on vast image examples to learn a more accurate Gaussian process (GP) regressor for single image dehazing. The GP regression learnt from these optimal examples is able to produce the transmission prediction with lower variance and thus renders high robustness. Extensive experiments on hazy images at various haze levels demonstrate the effectiveness of the proposed example searching compared with the state-of-the-art data-driven dehazing methods.
Similar content being viewed by others
Notes
All resultant images for these comparisons and testing hazy images are available at https://github.com/dlut-dimt/TVCJ.
References
Ancuti, C.O., Ancuti, C., Hermans, C., Bekaert, P.: A fast semi-inverse approach to detect and remove the haze from a single image. In: Asian Conference on Computer Vision, pp. 501–514. Springer (2011)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Berlin (2006)
Burger, H.C., Schuler, C.J., Harmeling, S.: Image denoising: can plain neural networks compete with BM3D? In: Computer Vision and Pattern Recognition, pp. 2392–2399. IEEE (2012)
Cai, B., Xu, X., Jia, K., Qing, C., Tao, D.: Dehazenet: an end-to-end system for single image haze removal. arXiv preprint arXiv:1601.07661 (2016)
Cao, Y., Brubaker, M.A., Fleet, D.J., Hertzmann, A.: Efficient optimization for sparse Gaussian process regression. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2013)
Chen, L., Lu, G., Zhang, D.: Effects of different Gabor filter parameters on image retrieval by texture. In: ACM International Conference Multimedia, pp. 273–278. Citeseer (2004)
Crete, F., Dolmiere, T., Ladret, P., Nicolas, M.: The blur effect: perception and estimation with a new no-reference perceptual blur metric. In: Rogowitz, BE., Pappas, TN., Daly, SJ. (eds.) Electronic Imaging 2007, pp. 64,920I–64,920I. International Society for Optics and Photonics (2007)
Domingos, P.: A few useful things to know about machine learning. Commun. ACM 55(10), 78–87 (2012)
Fan, X., Gao, R., Wang, Y.: Example-based haze removal with two-layer Gaussian process regressions. In: Keyser, J., Kim, Y.J., Wonka, P. (eds.) Pacific Graphics Short Papers. The Eurographics Association (2014). https://doi.org/10.2312/pgs.20141260
Fan, X., Liu, R., Huyan, K., Feng, Y., Luo, Z.: Self-reinforced cascaded regression for face alignment. In: AAAI (2018)
Fan, X., Wang, Y., Gao, R., Luo, Z.: Haze editing with natural transformations. Vis. Comput. 32, 137–147 (2016)
Fan, X., Wang, Y., Tang, X., Gao, R., Luo, Z.: Two-layer Gaussian process regression with example selection for image dehazing. IEEE Trans. Circuits Syst. Video Technol. (2016). https://doi.org/10.1109/TCSVT.2016.2592328
Fattal, R.: Single image dehazing. ACM Trans. Graph. 27(3), 72:1–72:9 (2008). https://doi.org/10.1145/1360612.1360671
Feng, Y., Liu, R., Fan, X., Huyan, K., Luo, Z.: Leveraging geometric correlation for input-adaptive facial landmark regression. In: IEEE International Conference on Multimedia and Expo (ICME), pp. 385–390 (2017)
Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example-based super-resolution. Comput. Graph. Appl. 22(2), 56–65 (2002)
Freeman, W.T., Pasztor, E.C., Carmichael, O.T.: Learning low-level vision. Int. J. Comput. Vis. 40(1), 25–47 (2000)
Frost, R., Armstrong, B.C., Siegelman, N., Christiansen, M.H.: Domain generality versus modality specificity: the paradox of statistical learning. Trends Cogn. Sci. 19(3), 117–125 (2015)
Gibson, K., Belongie, S., Nguyen, T.: Example based depth from fog. In: International Conference on Image Processing, pp. 728–732. IEEE (2013)
Gibson, K.B., Belongie, S.J., Nguyen, T.Q.: Example based depth from fog. In: International Conference on Image Processing, pp. 728–732. IEEE (2013)
He, H., Siu, W.C.: Single image super-resolution using Gaussian process regression. In: Computer Vision and Pattern Recognition, pp. 449–456 (2011)
He, K., Sun, J., Tang, X.: Guided image filtering. In: European Conference on Computer Vision, vol. 35(6), pp. 1397–1409 (2011). https://doi.org/10.1109/TPAMI.2012.213
He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341–2353 (2012). https://doi.org/10.1109/TPAMI.2010.168
Huynh-Thu, Q., Ghanbari, M.: Scope of validity of PSNR in image/video quality assessment. Electron. Lett. 44(13), 800–801 (2008)
Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: European Conference on Computer Vision, pp. 304–317. Springer (2008)
Kwon, Y., Kim, K.I., Tompkin, J., Kim, J.H., Theobalt, C.: Efficient learning of image super-resolution and compression artifact removal with semi-local Gaussian processes. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1792–1805 (2015)
Lazarogredilla, M., Quinonerocandela, J., Rasmussen, C.E., Figueirasvidal, A.R.: Sparse spectrum Gaussian process regression. J. Mach. Learn. Res. 11, 1865–1881 (2010)
Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., Yang, M.H.: Single image dehazing via multi-scale convolutional neural networks. In: European Conference on Computer Vision (2016)
Ren, X., Malik, J.: Learning a classification model for segmentation. In: International Conference on Computer Vision, pp. 10–17. IEEE (2003)
Saxena, A., Sun, M., Ng, A.Y.: Learning 3-d scene structure from a single still image. In: International Conference on Computer Vision (2007)
Schmidt, U., Rother, C., Nowozin, S., Jancsary, J., Roth, S.: Discriminative non-blind deblurring. In: Computer Vision and Pattern Recognition, pp. 604–611 (2013)
Settles, B.: Active Learning Literature Survey. Computer Sciences Technical Report 1648. University of Wisconsin-Madison (2010)
Silpaanan, C., Hartley, R.: Optimised kd-trees for fast image descriptor matching. In: Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008)
Sun, L., Hays, J.: Super-resolution from internet-scale scene matching. In: International Conference on Computational Photography, pp. 1–12. IEEE (2012)
Tan, R.: Visibility in bad weather from a single image. In: Computer Vision and Pattern Recognition, pp. 1–8 (2008). https://doi.org/10.1109/CVPR.2008.4587643
Tang, K., Yang, J., Wang, J.: Investigating haze-relevant features in a learning framework for image dehazing. In: Computer Vision and Pattern Recognition (2014)
Tang, X., Fan, X., Duan, Y., Luo, Z.: A fast training example searching algorithm for data-driven dehazing. In: International Conference on Digital Home (2016)
Yue, H., Sun, X., Yang, J., Wu, F.: CID: Combined image denoising in spatial and frequency domains using web images. In: Computer Vision and Pattern Recognition, pp. 2933–2940 (2014)
Zhao, X., Wang, S., Li, S., Li, J.: Passive image-splicing detection by a 2-d noncausal Markov model. IEEE Trans. Circuits Syst. Video Technol. 25(2), 185–199 (2015)
Zhu, Q., Mai, J., Shao, L.: A fast single image haze removal algorithm using color attenuation prior. IEEE Trans. Image Process. 24(11), 3522–3533 (2015)
Zoran, D., Isola, P., Krishnan, D., Freeman, W.T.: Learning ordinal relationships for mid-level vision. In: International Conference on Computer Vision, pp. 388–396 (2015)
Acknowledgements
This work is partially supported by the Natural Science Foundation of China under Grant Nos. 61572096, 61432003, and 61733002. The authors are grateful to Prof. Ming-Ting Sun at the University of Washington and Dr. Jue Wang at Megvii Inc. for their constructive discussions and suggestions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fan, X., Tang, X., Hou, M. et al. Fast example searching for input-adaptive data-driven dehazing with Gaussian process regression. Vis Comput 35, 565–577 (2019). https://doi.org/10.1007/s00371-018-1485-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-018-1485-y