Web image interpolation via weighted total least squares regression

Although ordinary least squares (OLS) regression achieves great success in clean image interpolation, its effectiveness is questionable in the scenario of web images which are usually compressed beforehand. The inherent flaw of OLS is that it is asymmetric, the perturbation is only confined on the right side of the linear system. It is not reasonable for web images. Considering the drawback of OLS, in this paper, we propose an efficient web image interpolation algorithm based on total least squares (TLS) regression. In the proposed method, small perturbations are allowed in both side of the system, which are optimized by TLS in a patch-based manner. Furthermore, we develop a weighted version of TLS to consider contribution diversity of different samples and patches in model estimation, which can efficiently remove the influence of outliers in regression. Experimental results on benchmark test images demonstrate the efficiency of our method.