“Spectral remapping for image downscaling” by Gastal and Oliveira

  • ©Eduardo Simões Lopes Gastal and Manuel M. Oliveira




    Spectral remapping for image downscaling


Session Title: Image and Light Field Manipulation



    We present an image downscaling technique capable of appropriately representing high-frequency structured patterns. Our method breaks conventional wisdom in sampling theory—instead of discarding high-frequency information to avoid aliasing, it controls aliasing by remapping such information to the representable range of the downsampled spectrum. The resulting images provide more faithful representations of their original counterparts, retaining visually-important details that would otherwise be lost. Our technique can be used with any resampling method and works for both natural and synthetic images. We demonstrate its effectiveness on a large number of images downscaled in combination with various resampling strategies. By providing an alternative solution for a long-standing problem, our method opens up new possibilities for image processing.


    1. E. H. Adelson. 1995. Checkershadow Illusion. http://web.mit.edu/persci/people/adelson/checkershadow_illusion.html. (1995). Accessed: 2017-01-05.Google Scholar
    2. T. Blu, P. Thcvenaz, and M. Unser. 2001. MOMS: Maximal-order interpolation of minimal support. IEEE TIP 10, 7 (2001), 1069–1080. Google ScholarDigital Library
    3. T. A. Davis. 2011. Algorithm 915, SuiteSparseQR: Multifrontal Multithreaded Rank-revealing Sparse QR Factorization. ACM Trans. Math. Softw. 38, 1 (2011), 8:1–8:22.Google ScholarDigital Library
    4. D. Gabor. 1946. Theory of Communication. Part 1: The Analysis of Information. Journal of the IEEE 93, 26 (Nov. 1946), 429–441. Google ScholarCross Ref
    5. E. J. Hannan. 1973. The Estimation of Frequency. Journal of Applied Probability 10, 3 (1973), 510–519. Google ScholarCross Ref
    6. F.J. Harris. 1978. On the Use of Windows for Harmonic Analysis with the Discrete Fourier Transform. Proc. of the IEEE 66, 1 (1978), 51–83. Google ScholarCross Ref
    7. C. Heil. 2007. History and Evolution of the Density Theorem for Gabor Frames. Journ. of Fourier Anal. and Applic. 13, 2 (2007), 113–166. Google ScholarCross Ref
    8. E. Jacobsen and P. Kootsookos. 2007. Fast, Accurate Frequency Estimators. IEEE Signal Process. Mag. 24, 3 (2007), 123–125. Google ScholarCross Ref
    9. J. Kopf, A. Shamir, and P. Peers. 2013. Content-adaptive Image Downscaling. ACM TOG 32, 6, Article 173 (Nov. 2013), 8 pages. Google ScholarDigital Library
    10. T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum. 2007. Learning to Detect A Salient Object. In IEEE CVPR. 1–8. Google ScholarCross Ref
    11. J. Mairal, F. Bach, and J. Ponce. 2014. Sparse Modeling for Image and Vision Processing. Foundations and Trends in C.G. and Vision 8, 2–3 (2014), 85–283.Google ScholarDigital Library
    12. S. G. Mallat. 1998. A Wavelet Tour of Signal Processing (2nd ed.). Academic Press.Google Scholar
    13. D. P. Mitchell and A. N. Netravali. 1988. Reconstruction Filters in Computer-graphics. In Proc. SIGGRAPH ’88. 221–228. Google ScholarDigital Library
    14. D. Nehab and H. Hoppe. 2014. A Fresh Look at Generalized Sampling. Foundations and Trends in C.G. and Vision 8, 1 (2014), 1–84. Google ScholarDigital Library
    15. B. A. Olshausen and D. J. Field. 1996. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381 (1996), 607–609. Google ScholarCross Ref
    16. A. V. Oppenheim and J. S. Lim. 1981. The importance of phase in signals. Proc. IEEE 69, 5 (1981), 529–541. Google ScholarCross Ref
    17. A. Cengiz Öztireli and Markus Gross. 2015. Perceptually Based Downscaling of Images. ACM TOG 34, 4, Article 77 (July 2015), 10 pages. Google ScholarDigital Library
    18. J. Portilla and E. P. Simoncelli. 2000. A Parametric Texture Model based on Joint Statistics of Complex Wavelet Coefficients. Int’l Journal of Computer Vision 40, 1 (2000), 49–71. Google ScholarDigital Library
    19. J. G. Proakis and D. K. Manolakis. 2007. Digital Signal Processing: Principles, Algorithms, and Applications. Pearson Education India.Google Scholar
    20. T. Quatieri and Rl McAulay. 1986. Speech Transformations Based on a Sinusoidal Representation. IEEE Transactions on Acoustics, Speech, and Signal Processing 34, 6 (1986), 1449–1464.Google ScholarCross Ref
    21. B. G. Quinn. 1989. Estimating the Number of Terms in a Sinusoidal Regression. Journal of Time Series Analysis 10, 1 (1989), 71–75. Google ScholarCross Ref
    22. E. Reinhard, M. Ashikhmin, B. Gooch, and P. Shirley. 2001. Color Transfer Between Images. IEEE Comput. Graph. Appl. 21, 5 (2001), 34–41. Google ScholarDigital Library
    23. D. C. Rife and R. R. Boorstyn. 1976. Multiple Tone Parameter Estimation From Discrete Time Observations. Bell System Technical Journal 55 (1976), 1389–1410. Google ScholarCross Ref
    24. L. Sacht and D. Nehab. 2015. Optimized quasi-interpolators for image reconstruction. IEEE TIP 24, 12 (2015), 5249–5259. Google ScholarCross Ref
    25. R. Samadani, T. A. Mauer, D. M. Berfanger, and J. H. Clark. 2010. Image Thumbnails That Represent Blur and Noise. IEEE TIP 19, 2 (2010), 363–373. Google ScholarDigital Library
    26. C. E. Shannon. 1949. Communication in the Presence of Noise. Proc. Institute of Radio Engineers 37, 1 (1949), 10–21. Google ScholarCross Ref
    27. J. O. Smith and X. Serra. 1987. PARSHL: An Analysis / Synthesis Program for Non-Harmonic Sounds Based on a Sinusoidal Representation. In Proc. of the Int’l Computer Music Conference.Google Scholar
    28. M. Trentacoste, R. Mantiuk, and W. Heidrich. 2011. Blur-Aware Image Downsampling. Computer Graphics Forum (2011). Google ScholarCross Ref
    29. M. Unser. 2000. Sampling-50 Years after Shannon. Proc. IEEE 88, 4 (2000), 569–587. Google ScholarCross Ref
    30. Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE TIP 13, 4 (2004), 600–612. Google ScholarDigital Library
    31. N. Weber, M. Waechter, S. C. Amend, S. Guthe, and M. Goesele. 2016. Rapid, Detail-preserving Image Downscaling. ACM TOG 35, 6, Article 205 (Nov. 2016), 6 pages.Google Scholar
    32. M. Zibulski and Y. Y. Zeevi. 1994. Frame Analysis of the Discrete Gabor-Scheme. IEEE Trans. on Sig. Proc. 42, 4 (1994), 942–945. Google ScholarDigital Library

ACM Digital Library Publication: