A Review of PDE Based Local Inpainting Methods

Abstract

Image inpainting is the process of recovering the damage areas in the images in an undetectable way, it is considered the important one of the subjects in image processing. There are many applications of image inpainting include the restoration of damaged images, paintings, and movies, to the removal of selected objects, such as text, lines, subtitles, publicity, and stamps. The main objective of inpainting is to reconstruct the missing region in such a way that the observer does not come to know that the image has been manipulated. Inpainting methods can be categorized into global and local methods, the global methods are applied to reconstruct the damaged areas in the image based on the information in the data of images that have the same content. While the local methods are used to reconstruct the missing regions based on the information in the rest parts of the image. There are several local methods proposed for image inpainting such as PDE-based inpainting (PDE-BI), exemplar-based inpainting (EBI), hybrid, and texture synthesis methods. In this paper, a review of different PDE and variational methods used for image inpainting is provided. Different PDE-BI methods like 2nd-and high-order of variational and PDE methods are discussed with its pros and cons.

Reconv: Repeated Convolutional Strategies for Advanced Image Inpainting

“…The main aim behind image restoration is to logically complete spaces remained by damaged portions of images [1]. Image inpainting remains a subject of active research because of its tremendous advantages for image editing features like object removal and image restoration which are very useful [2], [3] and [4]. The two categories of current methodologies are methods depending on learning and methods depending on nonlearning.…”

“…Image inpainting is commonly employed in image processing applications like elimination of superimposed text like dates, captions, as well as stamps in different images. The purpose of inpainting an image is to fill in vacant spaces in images with logical information and in addition, it manages further computer vision tasks like object detection, object identification, and semantic segmentation [2]. Despite the many benefits of this approach, retrieving suitable, rich, and distinctive textures for broad unstructured missing portions in high-quality photographs presents major challenges for image inpainting..…”

“…PDE works by diffusing image pixels from the target region's edge to its interior by propagating information from the border. Contextual information is moved from borders into holes in the direction of the isophotes by this method [1], [2].…”

“…Even though, this method is very effective in filling small regions, it tends to introduce some blurry effect while filling large textured regions. This occurs because PDE solutions frequently require the boundary and initial conditions to be provided [2]. The primary drawbacks of this model are that it performs inadequate when reconstructing large textured areas because the propagation process introduces blurring artefacts and there is insufficient explicit management of the edge pixels.…”

A Novel Image Inpainting Technique Based on Isotropic Diffusion

“…In addition, u can be calculated from the solution of minimization functional for the squared total variation. Heat equation was introduced as minimization energy functional as [15]:…”