Abstract
We address the problem of image upscaling in the form of single image super-resolution based on a dictionary of low- and high-resolution exemplars. Two recently proposed methods, Anchored Neighborhood Regression (ANR) and Simple Functions (SF), provide state-of-the-art quality performance. Moreover, ANR is among the fastest known super-resolution methods. ANR learns sparse dictionaries and regressors anchored to the dictionary atoms. SF relies on clusters and corresponding learned functions. We propose A+, an improved variant of ANR, which combines the best qualities of ANR and SF. A+ builds on the features and anchored regressors from ANR but instead of learning the regressors on the dictionary it uses the full training material, similar to SF. We validate our method on standard images and compare with state-of-the-art methods. We obtain improved quality (i.e. 0.2–0.7 dB PSNR better than ANR) and excellent time complexity, rendering A+ the most efficient dictionary-based super-resolution method to date.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
All the codes are publicly available at: http://www.vision.ee.ethz.ch/~timofter.
- 2.
For more results: http://www.vision.ee.ethz.ch/~timofter/.
References
Timofte, R., De Smet, V., Van Gool, L.: Anchored neighborhood regression for fast example-based super resolution. In: ICCV, pp. 1920–1927 (2013)
Sun, J., Xu, Z., Shum, H.-Y.: Image super-resolution using gradient profile prior. In: CVPR, pp. 1–8 (2008)
Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: ICCV, pp. 349–356 (2009)
Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution as sparse representation of raw image patches. In: CVPR, pp. 1–8 (2008)
Sun, J., Zhu, J., Tappen, M.F.: Context-constrained hallucination for image super-resolution. In: CVPR, pp. 231–238 (2010)
Michaeli, T., Irani, M.: Nonparametric blind super-resolution. In: ICCV, pp. 945–952 (2013)
Efrat, N., Glasner, D., Apartsin, A., Nadler, B., Levin, A.: Accurate blur models vs. image priors in single image super-resolution. In: ICCV, pp. 2832–2839 (2013)
Freeman, W.T., Pasztor, E.C., Carmichael, O.T.: Learning low-level vision. IJCV 40(1), 25–47 (2000)
Chang, H., Yeung, D.-Y., Xiong, Y.: Super-resolution through neighbor embedding. In: CVPR, pp. 275–282 (2004)
Bevilacqua, M., Roumy, A., Guillemot, C., Alberi Morel, M.-L.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: BMVC, pp. 1–10 (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 2011. LNCS, vol. 6920, pp. 711–730. Springer, Heidelberg (2012)
Yang, C.-Y., Yang, M.-H.: Fast direct super-resolution by simple functions. In: ICCV, pp. 561–568 (2013)
Roweis, S., Lawrence, S.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)
Timofte, R., Van Gool, L.: Adaptive and weighted collaborative representations for image classification. Pattern Recogn. Lett. 43, 127–135 (2014)
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 (2001)
Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)
De Smet, V., Namboodiri, V.P., Van Gool, L.J.: Nonuniform image patch exemplars for low level vision. In: WACV, pp. 23–30 (2013)
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, Part IV. LNCS, vol. 8692, pp. 184–199. Springer, Heidelberg (2014)
Acknowledgement
This work was partly supported by the ETH General Founding (OK) and the Flemish iMinds framework.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Timofte, R., De Smet, V., Van Gool, L. (2015). A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9006. Springer, Cham. https://doi.org/10.1007/978-3-319-16817-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-16817-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16816-6
Online ISBN: 978-3-319-16817-3
eBook Packages: Computer ScienceComputer Science (R0)