Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods. Recently, Pathak et al. [25] have introduced convolutional “context encoders” (CEs) for unsupervised feature learning through image completion tasks. With the additional help of adversarial training, CEs turned out to be a promising tool to complete complex structures in real inpainting problems. ...

Recent research has shown that inpainting with the Laplace or biharmonic operator has a high potential for image compression, if the stored data is optimised and sufficiently sparse. The goal of our paper is to connect these linear inpainting methods to sparsity concepts. To understand these relations, we explore the theory of Green’s functions. In contrast to most work in the mathematical lite...

The problem of inpainting involves reconstructing the missing areas of an image. Inpainting has many applications, such as reconstructing old damaged photographs or removing obfuscations from images. In this paper we present the directional diffusion algorithm for inpainting. Typical diffusion algorithms are bad at propagating edges from the image into the unknown masked regions. The directiona...

The Cahn-Hilliard equation has its origin in material sciences and serves as a model for phase separation and phase coarsening in binary alloys. A new approach in the class of fourth order inpainting algorithms is inpainting of binary images using the Cahn-Hilliard equation. We will present a generalization of this fourth order approach for grayvalue images. This is realized by using subgradien...

The aim of this article is to propose a new method for the inpainting problem. Inpainting is the problem of filling-in holes in images. We consider in this article the crack localization problem, which can be solved using the Dirichlet to Neumann approach and the topological gradient. In a similar way, we can define a Dirichlet and a Neumann inpainting problem. We then define a cost function me...

Patch-based (or “pattern-based”) inpainting, is a popular processing technique aiming at reconstructing missing regions in images, by iteratively duplicating blocks of known image data (patches) inside the area to fill in. This kind of method is particularly effective to process wide image areas, thanks to its ability to reconstruct textured data. Nevertheless, “pathological” geometric configur...

Image inpainting is an image restoration problem, in which image models play a critical role, as demonstrated by Chan, Kang and Shen’s recent inpainting schemes based on the bounded variation [10] and the elastica [9] image models. In the present paper, we propose two novel inpainting models based on the MumfordShah image model [37], and its high order correction — the Mumford-Shah-Euler image ...

Image inpainting has been widely used in practice to repair damaged/missing pixels of given images. Most of the existing inpainting techniques require knowing beforehand where those damaged pixels are, either given as a priori or detected by some pre-processing. However, in certain applications, such information neither is available nor can be reliably pre-detected, e.g. removing random-valued ...

Image Segmentation and Its Applications Based on the Mumford-Shah Model Xiaojun Du, Ph.D. Concordia University, 2011 Image segmentation is an important topic in computer vision and image processing. As a region-based (global) approach, the Mumford and Shah (MS) model is a powerful and robust segmentation technique as compared to edge-based (local) methods. In this thesis we apply the MS model t...

An edge-sensitive variational approach for the restoration of optical flow fields is presented. Real world optical flow fields are frequently corrupted by noise, reflection artifacts or missing local information. Still, applications may require dense motion fields. In this paper, we pick up image inpainting methodology to restore motion fields, which have been extracted from image sequences bas...