Image Inpainting Using Sparsity of the Transform Domain

TL;DR

This paper introduces a novel image inpainting technique leveraging the sparsity of transform domain coefficients, enhancing recovery of both structural and textured images by using sparsity patterns as side information.

Contribution

The method uniquely incorporates transform domain sparsity and side information to improve image inpainting performance over existing techniques.

Findings

Outperforms existing inpainting methods in objective measures

Effective for both structural and textured images

Utilizes sparsity patterns for improved recovery

Abstract

In this paper, we propose a new image inpainting method based on the property that much of the image information in the transform domain is sparse. We add a redundancy to the original image by mapping the transform coefficients with small amplitudes to zero and the resultant sparsity pattern is used as the side information in the recovery stage. If the side information is not available, the receiver has to estimate the sparsity pattern. At the end, the recovery is done by consecutive projecting between two spatial and transform sets. Experimental results show that our method works well for both structural and texture images and outperforms other techniques in objective and subjective performance measures.