Denoising

Denoising results

Remark: PSNR is calculated using each image's peak gray-level value. In order to properly visualize the results, the displayed images' contrast is stretched so that all the images cover the same gray-level range of [0,255].

References

[1] Zachevsky, Ido, and Zeevi, Yehoshua Y. "Statistics of Natural Stochastic Textures and Their Application in Image Denoising," (IEEE-TIP, 2016).
[2] Buades, Antoni, Bartomeu Coll, and J-M. Morel. "A non-local algorithm for image denoising," Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 2. IEEE, 2005.
[3] Starck, J-L., Emmanuel J. Candes, and David L. Donoho. "The curvelet transform for image denoising," Image Processing, IEEE Transactions on 11.6 (2002): 670-684.
[4] Dabov, Kostadin, et al. "Image denoising by sparse 3-D transform-domain collaborative filtering," Image Processing, IEEE Transactions on 16.8 (2007): 2080-2095.
[5] Zoran, Daniel, and Yair Weiss. "From learning models of natural image patches to whole image restoration," Computer Vision (ICCV), 2011 IEEE International Conference on. IEEE, 2011.
[6] Knaus, Claude, and Zwicker, Matthias. "Dual-Domain Image Denoising," Image Processing, IEEE Conference on (2013): 440-444.
[7] Foi, Alessandro, and Boracchi, Giacomo. "Foveated self-similarity in nonlocal image filtering," S&T/SPIE Electronic Imaging (pp. 829110-829110). International Society for Optics and Photonics, 2012.