Download
image upsampling via imposed edge statistics n.
Skip this Video
Loading SlideShow in 5 Seconds..
Image upsampling via Imposed Edge Statistics PowerPoint Presentation
Download Presentation
Image upsampling via Imposed Edge Statistics

Image upsampling via Imposed Edge Statistics

274 Vues Download Presentation
Télécharger la présentation

Image upsampling via Imposed Edge Statistics

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

  1. Image upsampling via Imposed Edge Statistics RaananFattal. ACM Siggraph 2007 Presenter: 이성호

  2. PreviousworkClassical approach • Nearest-Neighbor, Bilinear, Bicubic, Hann, Hamming, and Lanczos interpolation kernels. • assumption that • the image data is either spatially smooth or band-limited

  3. More sophisticated methods • [Su and Willis 2004] • Reduce the number of variables that are averaged • forms a noticeable block-like effect Bicubic Su and Willis 2004

  4. [Li and Orchard 2001] • Arbitrary edge orientation is implicitly matched • By estimating local intensity covariance • from the low-resolution image • Generating smooth curves and of reducing jaggies • Not sharp edges

  5. [Hertzmann et al. 2001] • Image Analogies

  6. [Freeman et al. 2002] • adding high-frequency patches • from a non-parametric set of examples • relating low and high resolutions • Sharpens edges and yields images with a detailed appearance • tends to introduce some irregularitiesinto the constructed image

  7. [Osher et al. 2003] • invert a blurring process • measures the L1 norm of the output image

  8. Assumptions on image upsampling • different upsampling techniques correspond to different assumptions: • images are smooth enough to be adequately approximated by polynomials • yields analytic polynomial-interpolation formulas • images are limited in band • yields a different family of low-pass filters • these assumptions are highly inaccurate • suffer from excessive blurriness and the other visual artifacts

  9. Edge-Frame Continuity Moduli • predict the spatial intensity differences • at the high-resolution based on the low-resolution input image

  10. Approach • Statistics of intensity differences • intensity conservation constraint • we discuss only gray scale images • later extend to handle color images

  11. Derivatives

  12. Image statistics

  13. edge-frame continuity modulus (EFCM)

  14. Upsampling using the EFCM

  15. Gauss-Markov Random Field model

  16. Color images • First we upsample the luminance channel • of the YUV color space • compute the absolute value of its luminance difference d1 d2 d3 d4

  17. Results High-res original Downsampled

  18. Bilinear Ours

  19. Simple Edge Sensitive New Edge-Directed

  20. magnified by a factor of 4

  21. magnified by a factor of 8

  22. magnified by a factor of 16

  23. objective error measurements between an upsampled image and the original ground-truth image (i.e., before downsampling). Structural Similarity Image Quality (SSIQ) described in [Wang et al. 2004]

  24. Implementations • implemented in C++ • Mobile Pentium-M, running at 2.1MHz • Upsample an image of 1282 pixels • to twice its resolution (2562). • 2 seconds • To a resolution of 10242 pixels • 22 seconds.

  25. Conclusions • Drawbacks: • Emphasize lack of texture and absence of fine-details • The jaggies artifact • Acutely twisted edges • involves more computations • than some of the existing techniques • generic behavior of edges does not accurately describe every particular case. • Further improve • Using higher-order edge properties • Such as curvature

  26. Appendix Numerical analysis on EFCM upsampling

  27. Lagrange multipliers

  28. Apply to the formula in this paper • Solve this linear system • with Conjugate Gradient-based Null Space method