Image inpainting

  title={Image inpainting},
  author={Marcelo Bertalm{\'i}o and Guillermo Sapiro and Vicent Caselles and Coloma Ballester},
  journal={Proceedings of the 27th annual conference on Computer graphics and interactive techniques},
Inpainting, the technique of modifying an image in an undetectable form, is as ancient as art itself. The goals and applications of inpainting are numerous, from the restoration of damaged paintings and photographs to the removal/replacement of selected objects. In this paper, we introduce a novel algorithm for digital inpainting of still images that attempts to replicate the basic techniques used by professional restorators. After the user selects the regions to be restored, the algorithm… 

Figures from this paper

Review On Image Portion Mixing With Background Using In-painting Technique

Inpainting is the technique of modifying an image in an imperceptible form, is a very old fine art itself. The goals and applications of inpainting are frequent from the restoration of damaged

Region Filling and Object Removal in Images using Criminisi Algorithm

An algorithm that enhances and extends a previously proposed algorithm and it provides faster inpainting and dynamic settings selection, which would allow the end user to obtain a collection of output images from which the finest result can be chosen.

Interactive Image Restoration Using Inpainting and Denoising

  • Nidhi AroraP. Kalra
  • Engineering
    2011 Third National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics
  • 2011
Digital in painting is the technique of filling in the missing regions of an image using information from the surrounding area in a visually indistinguishable way. In this paper, we try to improve

Image Inpainting – A Review of the Underlying Different Algorithms and Comparative Study of the Inpainting Techniques

This paper presents a comparative study and review of different image in painting techniques and the algorithms are analyzed theoretically as well as experimentally.

Image Inpainting - An Inclusive Review of the Underlying Algorithm and Comparative Study of the Associated Techniques

In this paper different types of image in painting algorithms are placed in juxtaposition and analysed theoretically as well as experimentally, based on which a ranking of algorithms will be established over different kinds of applications in diverse areas.

A Review of PDE Based Local Inpainting Methods

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.

Image in Painting Techniques: A survey

This proposed work presents a brief survey of different image inpainting techniques and comparative study of these techniques and provides a review of different techniques used for image Inpainting.

Survey on image portion mixing with background via in-painting technique

  • N. DangreP. Mohod
  • Art, Computer Science
    2015 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS)
  • 2015
An algorithm is presented that improves and extends a previously proposed algorithm and provides faster inpainting and is based on the exemplar based approach.

Image restoration using digital inpainting and noise removal

Object removal by region based filling inpainting

  • N. NeelimaM. Arulvani
  • Computer Science
    2013 International Conference on Emerging Trends in VLSI, Embedded System, Nano Electronics and Telecommunication System (ICEVENT)
  • 2013
A best-first algorithm is proposed in this paper in which the confidence in the synthesized pixel values is propagated in a manner similar to the propagation of information in inpainting, and the effectiveness of this algorithm in removing large occluding objects is demonstrated.



Filling-in by joint interpolation of vector fields and gray levels

A variational approach for filling-in regions of missing data in digital images is introduced. The approach is based on joint interpolation of the image gray levels and gradient/isophotes directions,

Interpolation of missing data in image sequences

A number of model based interpolation schemes tailored to the problem of interpolating missing regions in image sequences, and comparisons with earlier work using multilevel median filters demonstrate the higher reconstruction fidelity of the new interpolators.

Detection of missing data in image sequences

Heuristic and model-based methods for the detection of these missing data regions are presented in this paper, and their action on simulated and real sequences is compared.

Nontexture Inpainting by Curvature-Driven Diffusions

This third-order PDE model improves the second-order total variation inpainting model introduced earlier by Chan and Shen and is guided by the connectivity principle of human visual perception.

Combining frequency and spatial domain information for fast interactive image noise removal

This paper describes its fast iterative algorithm, based on a general framework of projection onto convex sets (POCS), that can reconstruct many contiguous noisy pixels in areas with large patterns while maintaining continuity of features such as lines.

Total variation based image restoration with free local constraints

  • L. RudinS. Osher
  • Mathematics
    Proceedings of 1st International Conference on Image Processing
  • 1994
A new total variation based approach was developed by Rudin, Osher and Fatemi to overcome the basic limitations of all smooth regularization algorithms, using the L/sup 1/ norm of the magnitude of a gradient, thus making discontinuous and nonsmooth solutions possible.

Nonlinear total variation based noise removal algorithms

Level lines based disocclusion

  • S. MasnouJ. Morel
  • Medicine
    Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)
  • 1998
It is shown in this paper how disocclusion can be performed by means of a level lines structure, which offers a reliable, complete and contrast-invariant representation of an image, in contrast to edges.

Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation, and magnification

The resulting active contour model offers a tractable implementation of the original Mumford-Shah model to simultaneously segment and smoothly reconstruct the data within a given image in a coupled manner and leads to a novel PDE-based approach for simultaneous image magnification, segmentation, and smoothing.

LCIS: a boundary hierarchy for detail-preserving contrast reduction

This work builds a similar hierarchy using multiple instances of a new low curvature image simplifier (LCIS), a partial differential equation inspired by anisotropic diffusion, and constructs a high detail, low contrast display image by compressing only the large features, then adding back all small details.