Adaptive Image Denoising by Mixture Adaptation (EM adaptation)

An EM adaptation method to learn effective image priors for image denoising

This package provides an implementation of an adaptive image denoising algorithm by mixture adaptation. The proposed method [1, 2] takes a generic prior learned from a generic external database and adapts it to the noisy image to generate a specific prior, which is then used for MAP denoising. The proposed algorithm is rigorously derived
from the Bayesian hyper-prior perspective and is further simplified to reduce the computational complexity. To have an overall evaluation of the denoising performance, please run the demo file: "demo.m". For additional information and citations, please refer to:
[1] E. Luo, S. H. Chan, and T. Q. Nguyen, "Adaptive Image Denoising by Mixture Adaptation," IEEE Trans. Image Process. 2016.
[2] S. H. Chan, E. Luo and T. Q. Nguyen, "Adaptive Patch-based Image Denoising by EM-adaptation," in Proc. IEEE Global Conf. Signal Information Process. (GlobalSIP'15), Dec. 2015.