Our robust PCA method can well fit more complex noise beyond conventional Gaussian, Laplacian, Sparse noise or any combinations of them: (best student poster runner-up in MLA2014)

Qian Zhao, Deyu Meng, Zongben Xu, Wangmeng Zuo, Lei Zhang. Robust principal component analysis with complex noise, Supplementary Material, ICML, 2014. Matlab code