Dynamic Content Adaptive Super-Resolution

  • Mei Chen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3211)


We propose an automatic adaptive approach to enhance the spatial resolution of an image sequence that allows different regions of the scene to be treated differently based on the content. Experimental results have shown its promise to avoid artifacts that otherwise might result from treating all regions of the scene in the same way during the resolution enhancement process. Moreover, it is able to dynamically tailor the image resolution enhancement process in an intelligent way. In particular, it can deploy processing resources to different regions of the scene at varying computational intensity levels to achieve high quality resolution enhancement in an efficient way.


Motion Vector Reference Image Motion Class Resolution Enhancement Motion Segmentation 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Baker, S., Kanade, T.: Hallucinating Faces, Technical Report CMU-RI-TR-99-32, The Robotics Institute, Carnegie Mellon University (1999) Google Scholar
  2. 2.
    Baker, S., Kanade, T.: Limits on Super-resolution and How to Break Them. In: Proceedings of CVPR 2000, Hilton Head, South Carolina, pp. 372–279 (2000)Google Scholar
  3. 3.
    Borman, S., Stevenson, R.L.: Spatial Resolution Enhancement of Low-Resolution Image Sequences: A Comprehensive Review with Directions for Future Research, Technical Report, University of Notre Dame (1998) Google Scholar
  4. 4.
    Bose, N.K., Kim, H.C., Valenzuela, H.M.: Recursive Implementation of Total Least Squares Algorithm for Image Reconstruction from Noisy, Undersampled Multiframes. In: Proceedings of ASSP1993, Minneapolis, MN, vol. 5, pp. 269–272 (1993)Google Scholar
  5. 5.
    Elad, M., Feuer, A.: Restoration of Single Super-resolution Image from Several Blurred, Noisy and Down-sampled Measured Images. IEEE Trans. on Image Processing 6(12), 1646–1658 (1997)CrossRefGoogle Scholar
  6. 6.
    Hardie, R.C., Barnard, K.J., Amstrong, E.E.: Joint MAP Registration and Highresolution Image Estimation Using a Sequence of Undersampled Images. IEEE Trans. on Image Processing 6(12), 1621–1633 (1997)CrossRefGoogle Scholar
  7. 7.
    Higham, N.J.: A Survey of Componentwise Perturbation Theory in Numerical Linear Algebra. In: Gautschi, W. (ed.) Mathematics of Computation 1943–1993: A Half Century of Computational Mathematics Proceedings of Symposia in Applied Mathematics, vol. 48, pp. 49–77. American Mathematical Society, Providence (1994)Google Scholar
  8. 8.
    Huang, T.S., Tsai, R.: Multi-frame Image Restoration and Registration. Advances in Computer Vision and Image Processing 1, 317–339 (1984)Google Scholar
  9. 9.
    Irani, M., Peleg, S.: Improving Resolution by Image Restoration. Computer Vision, Graphics, and Image Processing 53, 231–239 (1991)Google Scholar
  10. 10.
    Schultz, R., Stevenson, R.: Extraction of High-resolution Frames from Video Sequences. IEEE Trans. on Image Processing 5(6), 996–1011 (1996)CrossRefGoogle Scholar
  11. 11.
    Xu, S.: The Theory and Methods of Matrix Computation. Peking University Press, Chinese (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Mei Chen
    • 1
  1. 1.Hewlett-Packard LaboratoriesPalo AltoU.S.A

Personalised recommendations