Image Inpainting by Adaptive Fusion of Variable Spline Interpolations

TL;DR

This paper introduces an adaptive spline interpolation method for image inpainting, specifically targeting restoration of old, scratched images by considering edge information and variable neighbor pixels, resulting in improved quality and efficiency.

Contribution

The paper proposes a novel adaptive spline interpolation technique that incorporates edge detection and variable neighbor consideration for enhanced image inpainting.

Findings

Improved PSNR and SSIM metrics on the Kodak dataset.

Faster runtime compared to existing methods.

Effective restoration of scratched old images.

Abstract

There are many methods for image enhancement. Image inpainting is one of them which could be used in reconstruction and restoration of scratch images or editing images by adding or removing objects. According to its application, different algorithmic and learning methods are proposed. In this paper, the focus is on applications, which enhance the old and historical scratched images. For this purpose, we proposed an adaptive spline interpolation. In this method, a different number of neighbors in four directions are considered for each pixel in the lost block. In the previous methods, predicting the lost pixels that are on edges is the problem. To address this problem, we consider horizontal and vertical edge information. If the pixel is located on an edge, then we use the predicted value in that direction. In other situations, irrelevant predicted values are omitted, and the average of rest values is used as the value of the missing pixel. The method evaluates by PSNR and SSIM metrics on the Kodak dataset. The results show improvement in PSNR and SSIM compared to similar procedures. Also, the run time of the proposed method outperforms others.