Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

Radu Timofte, Vincent De Smet, and Luc Van Gool

ICCV 2013 Submission ID 1774

This is the supplementary material with results (images, PSNR, and running-time values) for all the methods as proposed or used in the paper.
The settings are the ones from the paper, we use the same evaluation procedure as in Zeyde et al, 'Curves and Surfaces', 2010.

(Note that it is a re-run, there might be some slight insignificant running time differences compared to the paper.)

Please click on the PSNR result values to see the grayscale image output of each method.

Set14 magnification x3 results (images, PSNR, times)(Table 1 in the paper)
Set5 magnification x2 results (images, PSNR, times)(Table 2 in the paper)
Set5 magnification x3 results (images, PSNR, times)(Table 2 in the paper)
Set5 magnification x4 results (images, PSNR, times)(Table 2 in the paper)

Paper.
Source codes.
Supplementary material in a Zip archive.

Check our new A+ method, improves in both, speed and quality (+0.7dB improvements) !

[29]	R. Timofte, V. De Smet, and L. Van Gool. A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution. In Asian Conference on Computer Vision (ACCV 2014), 1-5 November 2014, Singapore. [ bib \| pdf \| Supplementary material \| Source codes ]