Blind Image Deblurring with Outlier Handling Supplemental Material

In this supplemental material, we analyze how the proposed blind image deblurring method performs on images with outliers and demonstrate the effectiveness of the proposed data fidelity term in Section 1. Section 2 provides more analysis of the proposed algorithm. We quantitatively evaluate the proposed algorithm and compare it against existing blind deblurring methods on the datasets with outliers and random noise in Section 3. We further evaluate the proposed method on publicly available datasets [8] as well as [15] and show that it performs well against the state-of-the-art deblurring methods in Section 4. The proposed non-uniform deblurring algorithm is presented in Sections 5. More visual comparisons are shown in Section 6.