Image Inpainting via Singular Value Thresholding

Abstract

This paper proposes an inpainting technique based on the singular value thresholding (SVT) algorithm for matrix completion. The SVT algorithm computes the missing elements of a matrix so that the resultant matrix is an approximate of the completion with least rank. It can be implemented by a straightforward iteration procedure which performs singular value decompositions followed by a soft thresholding on the singular values. Experimental results show that the technique can effectively recover texture parts of damaged images.