Simultaneous structure and texture image inpainting

TLDR

The paper proposes an algorithm that simultaneously fills missing image regions with both structure and texture. The method decomposes the image into a bounded‑variation structure component and a texture component, inpaints the structure part, synthesizes texture in the missing area, and then recombines the two components. Experiments on real images demonstrate that this combined approach outperforms separate treatments and yields superior restoration quality.

Abstract

An algorithm for the simultaneous filling-in of texture and structure in regions of missing image information is presented in this paper. The basic idea is to first decompose the image into the sum of two functions with different basic characteristics, and then reconstruct each one of these functions separately with structure and texture filling-in algorithms. The first function used in the decomposition is of bounded variation, representing the underlying image structure, while the second function captures the texture and possible noise. The region of missing information in the bounded variation image is reconstructed using image inpainting algorithms, while the same region in the texture image is filled-in with texture synthesis techniques. The original image is then reconstructed adding back these two sub-images. The novel contribution of this paper is then in the combination of these three previously developed components, image decomposition with inpainting and texture synthesis, which permits the simultaneous use of filling-in algorithms that are suited for different image characteristics. Examples on real images show the advantages of this proposed approach.