# Exemplar-Based Image Inpainting Using a Modified Priority Definition

## TL;DR

This paper introduces a new method for image inpainting that improves the recovery of image geometry and textures by using a modified priority definition.

## Contribution

The novel contribution is an independent strategy with a new priority definition for exemplar-based image inpainting.

## Key findings

- The new priority definition improves the recovery of image geometry and textures.
- An automatic algorithm estimates steps for the new priority definition.
- The method outperforms competitive approaches in image inpainting.

## Abstract

Exemplar-based algorithms are a popular technique for image inpainting. They mainly have two important phases: deciding the filling-in order and selecting good exemplars. Traditional exemplar-based algorithms are to search suitable patches from source regions to fill in the missing parts, but they have to face a problem: improper selection of exemplars. To improve the problem, we introduce an independent strategy through investigating the process of patches propagation in this paper. We first define a new separated priority definition to propagate geometry and then synthesize image textures, aiming to well recover image geometry and textures. In addition, an automatic algorithm is designed to estimate steps for the new separated priority definition. Comparing with some competitive approaches, the new priority definition can recover image geometry and textures well.