Object removal by exemplar-based inpainting

  title={Object removal by exemplar-based inpainting},
  author={Antonio Criminisi and Patrick P{\'e}rez and Kentaro Toyama},
  journal={2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.},
  • A. CriminisiP. PérezK. Toyama
  • Published 18 June 2003
  • Computer Science
  • 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
A new algorithm is proposed for removing large objects from digital images. The challenge is to fill in the hole that is left behind in a visually plausible way. In the past, this problem has been addressed by two classes of algorithms: (i) "texture synthesis" algorithms for generating large image regions from sample textures, and (ii) "inpainting" techniques for filling in small image gaps. The former work well for "textures" - repeating two dimensional patterns with some stochasticity; the… 

Region filling and object removal by exemplar-based image inpainting

The simultaneous propagation of texture and structure information is achieved by a single, efficient algorithm that combines the advantages of two approaches: exemplar-based texture synthesis and block-based sampling process.


This paper proposes a best-first algorithm in which the confidence in the synthesized pixel values is propagated in a manner similar to the propagation of information in inpainting, and achieves simultaneous propagation of texture and structure information by a single, efficient algorithm.

Object removal by depth-wise image inpainting

This paper uses depth map of an image to find the order of all the objects in the target image and a database of multi-views of objects to fill the holes and proposes a method called Keyview Extraction to reduce the size of the database.

Image Enhancement and Restoration by Image Inpainting

This paper presents efficient algorithm that combines the advantages of structural, texture and exemplar techniques and proposes a best-first algorithm in which the confidence in the synthesized pixel values is propagated in a manner similar to the propagation of information in inpainting.

Patch-based Texture Synthesis for Image Inpainting

A novel framework is introduced to find several optimal candidate patches and generate a new texture patch in the process, and a geometric constraint metric is formally defined that is applied directly to the patch synthesis procedure.

Dyer Object Removal Using Exemplar-Based Inpainting

With this algorithm, the gap will be filled with non-blur textures, while at the same time preserve and extend the linear structure of the surrounding area, using Criminisi’s algorithm.

Analysis of Image Inpainting Techniques with Exemplar, Poisson, Successive Elimination and 8 Pixel Neighborhood Methods

A novel and efficient algorithm is presented that fills the hole by exemplar-based synthesis and the simultaneous propagation of texture and structure information is achieved by a single, efficient algorithm.

Exemplar Method Based Image Inpainting

A computationally efficient algorithm by a patch-based sampling process that propagates the structure well and produces some amazing results when inpainting images where complex salient structures exist in the missing regions.

Combining Texture Synthesis and Diffusion for Image Inpainting

A new algorithm dedicated to both types of images, to decompose the original image into a structure and a texture image and a comparison with some existing methods on different natural images shows the strength of the proposed approach.

A Structure-Synthesis Image Inpainting Algorithm Based on Morphological Erosion Operation

A new inpainting algorithm, which implements the filling of damaged region based on morphological erosion and structure feature replication, which can retain isophote continuity by propagating both texture and structure characteristics information of the known patch into the damaged region, and output a complete, natural-looking and non-blurred image.



Simultaneous structure and texture image inpainting

The novel contribution of the paper is the combination of these three previously developed components: image decomposition with inpainting and texture synthesis, which permits the simultaneous use of filling-in algorithms that are suited for different image characteristics.

Image inpainting

A novel algorithm for digital inpainting of still images that attempts to replicate the basic techniques used by professional restorators, and does not require the user to specify where the novel information comes from.

Image replacement through texture synthesis

This work proposes a technique based on Heeger and Bergen's texture synthesis algorithm (1995), which can be substituted with a synthetic texture derived from another portion of the image by integrating a composition step into the aforementioned algorithm.

Synthesizing natural textures

The algorithm is extended to allow direct user input for interactive control over the texture synthesis process, which allows the user to indicate large-scale properties of the texture appearance using a standard painting-style interface, and to choose among various candidate textures the algorithm can create by performing different number of iterations.

A variational model for filling-in gray level and color images

A variational approach for filling-in regions of missing data in gray-level and color images is introduced, based on joint interpolation of the image gray-levels and gradient/isophores directions, smoothly extending in an automatic fashion the isophote lines into the holes ofMissing data.

Image analogies

This paper describes a new framework for processing images by example, called “image analogies,” based on a simple multi-scale autoregression, inspired primarily by recent results in texture synthesis.

A Non-Hierarchical Procedure for Re-Synthesis of Complex Textures

It is shown that the accurate reproduction of features in the input texture depends on the order in which pixels are added to the output image, which is capable of reproducing large features even if only the interactions of nearby pixels are considered.

Fast texture synthesis using tree-structured vector quantization

This paper presents an efficient algorithm for realistic texture synthesis derived from Markov Random Field texture models and generates textures through a deterministic searching process that accelerates this synthesis process using tree-structured vector quantization.

Computational models for texture analysis and texture synthesis

Although the success of texture synthesis is highly dependent on the texture itself and the modeling method chosen, general conclusions regarding the performance of various techniques are given.

Image quilting for texture synthesis and transfer

This work uses quilting as a fast and very simple texture synthesis algorithm which produces surprisingly good results for a wide range of textures and extends the algorithm to perform texture transfer — rendering an object with a texture taken from a different object.