Advertisement

A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution

  • Radu TimofteEmail author
  • Vincent De Smet
  • Luc Van Gool
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9006)

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.

Keywords

Training Sample Neighborhood Size Sparse Code Convolutional Neural Network Dictionary Size 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgement

This work was partly supported by the ETH General Founding (OK) and the Flemish iMinds framework.

References

  1. 1.
    Timofte, R., De Smet, V., Van Gool, L.: Anchored neighborhood regression for fast example-based super resolution. In: ICCV, pp. 1920–1927 (2013)Google Scholar
  2. 2.
    Sun, J., Xu, Z., Shum, H.-Y.: Image super-resolution using gradient profile prior. In: CVPR, pp. 1–8 (2008)Google Scholar
  3. 3.
    Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: ICCV, pp. 349–356 (2009)Google Scholar
  4. 4.
    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)Google Scholar
  5. 5.
    Sun, J., Zhu, J., Tappen, M.F.: Context-constrained hallucination for image super-resolution. In: CVPR, pp. 231–238 (2010)Google Scholar
  6. 6.
    Michaeli, T., Irani, M.: Nonparametric blind super-resolution. In: ICCV, pp. 945–952 (2013)Google Scholar
  7. 7.
    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)Google Scholar
  8. 8.
    Freeman, W.T., Pasztor, E.C., Carmichael, O.T.: Learning low-level vision. IJCV 40(1), 25–47 (2000)CrossRefzbMATHGoogle Scholar
  9. 9.
    Chang, H., Yeung, D.-Y., Xiong, Y.: Super-resolution through neighbor embedding. In: CVPR, pp. 275–282 (2004)Google Scholar
  10. 10.
    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)Google Scholar
  11. 11.
    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) CrossRefGoogle Scholar
  12. 12.
    Yang, C.-Y., Yang, M.-H.: Fast direct super-resolution by simple functions. In: ICCV, pp. 561–568 (2013)Google Scholar
  13. 13.
    Roweis, S., Lawrence, S.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRefGoogle Scholar
  14. 14.
    Timofte, R., Van Gool, L.: Adaptive and weighted collaborative representations for image classification. Pattern Recogn. Lett. 43, 127–135 (2014)CrossRefGoogle Scholar
  15. 15.
    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)Google Scholar
  16. 16.
    Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)CrossRefMathSciNetGoogle Scholar
  17. 17.
    De Smet, V., Namboodiri, V.P., Van Gool, L.J.: Nonuniform image patch exemplars for low level vision. In: WACV, pp. 23–30 (2013)Google Scholar
  18. 18.
    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) CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Radu Timofte
    • 1
    Email author
  • Vincent De Smet
    • 2
  • Luc Van Gool
    • 1
    • 2
  1. 1.CVL, D-ITETETH ZürichZürichSwitzerland
  2. 2.VISICS, ESAT/PSIKU LeuvenLeuvenBelgium

Personalised recommendations