Abstract
Conventional coupled dictionary learning approaches are designed for noiseless image super-resolution (SR), but quite sensitive to noisy images. We find the cause is the commonly used \(\ell _2\)-norm coefficients transition term. In this paper, we propose a robust \(\ell _1\)-norm solution by introducing two sub-terms: LR coefficient sparsity constraint term and HR coefficient conversion term, which are able to prevent the noise transmission from noisy input to output. By incorporating our simple yet effective non-linear model inspired by auto-encoder, the proposed \(\ell _1\)-norm dictionary learning achieves a more accurate coefficients conversion. Moreover, we bring the non-local similarity constraint from pixel domain to the sparse coefficients optimization. The improved sparse representation further enhances SR inference on both noisy and noiseless images. Using standard metrics, we show that results are significantly clearer than state-of-the-arts on noisy images and sharper on denoised images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The matrix \(\mathbf {L}\) (non-local constraint) is applied to regularize \(\alpha _h\) as the function (4).
References
Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE. Trans. Image Process. 19, 2861–2873 (2010)
Yang, J., Wang, Z., Lin, Z., Cohen, S., Huang, T.: Coupled dictionary training for image super-resolution. IEEE. Trans. Image Process. 21, 3467–3478 (2012)
Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Boissonnat, J.-D., Chenin, P., Cohen, A., Gout, C., Lyche, T., Mazure, M.-L., Schumaker, L. (eds.) Curves and Surfaces 2010. LNCS, vol. 6920, pp. 711–730. Springer, Heidelberg (2012). doi:10.1007/978-3-642-27413-8_47
Wang, S., Zhang, L., Liang, Y., Pan, Q.: Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis. In: CVPR, pp. 2216–2223. IEEE (2012)
Huang, D.A., Wang, Y.C.F.: Coupled dictionary and feature space learning with applications to cross-domain image synthesis and recognition. In: ICCV, pp. 2496–2503. IEEE (2013)
He, L., Qi, H., Zaretzki, R.: Beta process joint dictionary learning for coupled feature spaces with application to single image super-resolution. In: CVPR, pp. 345–352. IEEE (2013)
Timofte, R., De, V., Van Gool, L.: Anchored neighborhood regression for fast example-based super-resolution. In: ICCV, pp. 1920–1927. IEEE (2013)
Timofte, R., De Smet, V., Van Gool, L.: A+: adjusted anchored neighborhood regression for fast super-resolution. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9006, pp. 111–126. Springer, Heidelberg (2015). doi:10.1007/978-3-319-16817-3_8
Peleg, T., Elad, M.: A statistical prediction model based on sparse representations for single image super-resolution. IEEE. Trans. Image Process. 23, 2569–2582 (2014)
Schulter, S., Leistner, C., Bischof, H.: Fast and accurate image upscaling with super-resolution forests. In: CVPR, pp. 3791–3799. IEEE (2015)
Timofte, R., Rothe, R., Van Gool, L.: Seven ways to improve example-based single image super resolution. arXiv preprint arxiv:1511.02228 (2015)
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks (2015). arXiv preprint arxiv:1511.04587
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2, 183–202 (2009)
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE. Trans. Pattern Anal. Mach. Intell. 38, 295–307 (2015)
Dai, D., Timofte, R., Van Gool, L.: Jointly optimized regressors for image super-resolution. In: Computer Graphics Forum, Wiley Online Library, pp. 95–104 (2015)
Singh, A., Porikli, F., Ahuja, N.: Super-resolving noisy images. In: CVPR, pp. 2846–2853. IEEE (2014)
Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: CVPR, pp. 60–65. IEEE (2005)
Zhang, K., Tao, D., Gao, X., Li, X., Xiong, Z.: Learning multiple linear mappings for efficient single image super-resolution. IEEE. Trans. Image Process. 24, 846–861 (2015)
Protter, M., Elad, M., Takeda, H., Milanfar, P.: Generalizing the nonlocal-means to super-resolution reconstruction. IEEE. Trans. Image Process. 18, 36–51 (2009)
Chen, X., Lin, Q., Kim, S., Carbonell, J.G., Xing, E.P., et al.: Smoothing proximal gradient method for general structured sparse regression. Ann. Appl. Stat. 6, 719–752 (2012)
Chalasani, R., Principe, J.C.: Deep predictive coding networks. arXiv preprint arxiv:1301.3541 (2013)
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans. Image Process. 16, 2080–2095 (2007)
Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 184–199. Springer, Heidelberg (2014). doi:10.1007/978-3-319-10593-2_13
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV, pp. 416–423. IEEE (2001)
Acknowledgments
This work is supported by the National Basic Research Program (973 Program) of China (No. 2013CB329402), the Fund for Foreign Scholars in University Research and Teaching Programs (the 111 Project) (No. B07048), the Program for Cheung Kong Scholars and Innovative Research Team in University (No. IRT 15R53), and JSPS Grants-in-Aid for Scientific Research C (No. 15K00236) for funding.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Yue, B., Wang, S., Liang, X., Jiao, L. (2017). Robust Noisy Image Super-Resolution Using \(\ell _1\)-norm Regularization and Non-local Constraint. In: Chen, CS., Lu, J., Ma, KK. (eds) Computer Vision – ACCV 2016 Workshops. ACCV 2016. Lecture Notes in Computer Science(), vol 10116. Springer, Cham. https://doi.org/10.1007/978-3-319-54407-6_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-54407-6_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-54406-9
Online ISBN: 978-3-319-54407-6
eBook Packages: Computer ScienceComputer Science (R0)