Advertisement

Interactive Super-Resolution through Neighbor Embedding

  • Jian Pu
  • Junping Zhang
  • Peihong Guo
  • Xiaoru Yuan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5996)

Abstract

Learning based super-resolution can recover high resolution image with high quality. However, building an interactive learning based super-resolution system for general images is extremely challenging. In this paper, we proposed a novel GPU-based Interactive Super-Resolution system through Neighbor Embedding (ISRNE). Random projection tree (RPtree) with manifold sampling is employed to reduce the number of redundant image patches and balance the node size of the tree. Significant performance improvement is achieved through the incorporation of a refined GPU-based brute force kNN search with a matrix-multiplication-like technique. We demonstrate 200-300 times speedup of our proposed ISRNE system with experiments in both small size and large size images.

Keywords

High Resolution Image Brute Force Image Patch Large Size Image Neighbor Embedding 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lin, Z.C., He, J.F., Tang, X.O., Tang, C.K.: Limits of learning-based superresolution algorithm. In: Proceedings of IEEE CVPR, pp. 1–7 (2007)Google Scholar
  2. 2.
    Freeman, W.T., Pasztor, E.C., Carmichael, O.T.: Learning low-level vision. International Journal of Computer Vision 40(1), 25–47 (2000)zbMATHCrossRefGoogle Scholar
  3. 3.
    Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example based superresolution. IEEE Computer Graphics and Applications 22(2), 56–65 (2002)CrossRefGoogle Scholar
  4. 4.
    Chang, H., Yeung, D.Y., Xiong, Y.: Super-resolution through neighbor embedding. In: Proceedings of IEEE CVPR, pp. 275–282 (2004)Google Scholar
  5. 5.
    Wei, F., Yeung, D.Y.: Image hallucination using neighbor embedding over visual primitive manifolds. In: Proceedings of IEEE CVPR, pp. 1–7 (2007)Google Scholar
  6. 6.
    Yang, J.C., Wright, J., Ma, Y., Huang, T.: Image super-resolution as sparse representation of raw image patches. In: Proceedings of IEEE CVPR, pp. 1–8 (2008)Google Scholar
  7. 7.
    Su, K., Tian, Q., Xue, Q., Sebe, N., Ma, J.: Neighborhood issue in single-frame image super-resolution. In: Proceedings of IEEE ICME, pp. 1122–1125 (2005)Google Scholar
  8. 8.
    Gunturk, B.K., Batur, A.U., Altunbasak, Y., Hayes III, M.H., Mersereau, R.M.: Eigenface-domain super-resolution for face recognition. IEEE Trans. Image Proc. 12(5), 597–606 (2003)CrossRefGoogle Scholar
  9. 9.
    Liu, C., Shum, H.Y., Freeman, W.T.: Face hallucination: Theory and practice. International Journal of Computer Vision 75(1), 115–134 (2007)CrossRefGoogle Scholar
  10. 10.
    Baker, S., Kanade, T.: Limits on super-resolution and how to break them. IEEE Trans. PAMI 24(9), 1167–1183 (2002)Google Scholar
  11. 11.
    Freund, Y., Dasgupta, S., Kabra, M., Verma, N.: Learning the structure of manifolds using random projections. In: NIPS, pp. 473–480 (2008)Google Scholar
  12. 12.
    Dasgupta, S., Freund, Y.: Random projection trees and low dimensional manifolds. Technical Report CS2007-0890, UCSD (2007)Google Scholar
  13. 13.
    Garcia, V., Debreuve, E., Barlaud, M.: Fast k nearest neighbor search using gpu. In: CVPR Workshop on Computer Vision on GPU, pp. 1–7 (2008)Google Scholar
  14. 14.
    Bishop, C.M., Blake, A., Marthi, B.: Super-resolution enhancement of video. In: Proceedings 9th International Conference on Artificial Intelligence and Statistics (2003)Google Scholar
  15. 15.
    Liu, C., Shum, H.Y., Zhang, C.S.: A two-step approach to hallucinating faces: Global parametric model and local nonparametric model. In: Proceedings of IEEE CVPR, pp. 192–198 (2001)Google Scholar
  16. 16.
    Qiao, Y.L., Pan, J.S., Sun, S.H.: Improved partial distance search for k nearest-neighbor classification. In: Proceedings of IEEE ICME, vol. 2, pp. 1275–1278 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Jian Pu
    • 1
  • Junping Zhang
    • 1
  • Peihong Guo
    • 2
  • Xiaoru Yuan
    • 2
  1. 1.Shanghai Key Lab of Intelligent Information Processing, School of Computer ScienceFudan UniversityShanghaiChina
  2. 2.Key Laboratory of Machine Perception (Ministry of Education), School of EECSPeking UniversityBeijingChina

Personalised recommendations