HySim: An Efficient Hybrid Similarity Measure for Patch Matching in Image Inpainting

TL;DR

This paper introduces HySim, a hybrid similarity measure combining Chebychev and Minkowski distances, to improve patch matching in image inpainting, especially useful when data is limited or of low quality.

Contribution

The paper proposes a novel hybrid similarity measure, HySim, that enhances patch matching in image inpainting by combining strengths of Chebychev and Minkowski distances.

Findings

HySim improves patch matching accuracy.

The approach yields higher quality inpainting results.

It outperforms traditional SSD-based methods.

Abstract

Inpainting, for filling missing image regions, is a crucial task in various applications, such as medical imaging and remote sensing. Trending data-driven approaches efficiency, for image inpainting, often requires extensive data preprocessing. In this sense, there is still a need for model-driven approaches in case of application constrained with data availability and quality, especially for those related for time series forecasting using image inpainting techniques. This paper proposes an improved modeldriven approach relying on patch-based techniques. Our approach deviates from the standard Sum of Squared Differences (SSD) similarity measure by introducing a Hybrid Similarity (HySim), which combines both strengths of Chebychev and Minkowski distances. This hybridization enhances patch selection, leading to high-quality inpainting results with reduced mismatch errors. Experimental results proved the effectiveness of our approach against other model-driven techniques, such as diffusion or patch-based approaches, showcasing its effectiveness in achieving visually pleasing restorations.