Inpainting

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search
Main article: Image editing
Original and restored image

Inpainting is the process of reconstructing lost or deteriorated parts of images and videos. In the museum world, in the case of a valuable painting, this task would be carried out by a skilled art conservator or art restorer. In the digital world, inpainting (also known as image interpolation or video interpolation) refers to the application of sophisticated algorithms to replace lost or corrupted parts of the image data (mainly small regions or to remove small defects).

Applications[edit]

There are many objectives and applications of this technique.

In photography and cinema, it is used for film restoration, to reverse the deterioration (e.g., cracks in photographs or scratches and dust spots in film; see infrared cleaning). It is also used for removing red-eye, the stamped date from photographs and removing objects to creative effect.

This technique can be used to replace the lost blocks in the coding and transmission of images, for example, in a streaming video. It can also be used to remove logos in videos.

Deep learning neural network based inpainting can be used for decensoring images.[1]

Methods[edit]

In painting[edit]

Inpainting is rooted in the restoration of images. Traditionally, inpainting has been done by professional restorers. The underlying methodology of their work is as follows:

  • The global picture determines how to fill in the gap. The purpose of inpainting is to restore the unity of the work.
  • The structure of the gap surroundings is supposed to be continued into the gap. Contour lines that arrive at the gap boundary are prolonged into the gap.
  • The different regions inside a gap, as defined by the contour lines, are filled with colors matching for those of its boundary.
  • The small details are painted, i.e. “texture” is added.

Computerized[edit]

Since the wide applications of digital camera and the digitalization of old photos, inpainting has become an automatic process that is performed on digital images. More than scratch removing, the inpainting techniques are also applied to object removal, text removal and other automatic modifications of images and videos. Furthermore, they can also be observed in applications like image compression and super resolution.

Three main groups of 2D image inpainting algorithms can be found in literature. The first one to be noted is structural inpainting, the second one is texture inpainting and the last one is a combination of these two techniques. All these inpainting methods have one thing in common - they use the information of the known or undestroyed image areas in order to fill the gap.

Structural inpainting[edit]

Structural inpainting uses geometric approaches[clarification needed (What does "geometric approaches" mean in this context?)] for filling in the missing information in the region which should be inpainted. These algorithms focus on the consistency of the geometric structure.[clarification needed (What is "the geometric structure" referred to?)]

Textural inpainting[edit]

Like everything else the structural inpainting methods have both advantages and disadvantages. The main problem is that all the structural inpainting methods are not able to restore texture. Texture has a repetitive pattern which means that a missing portion cannot be restored by continuing the level lines into the gap.[clarification needed (What are "level lines"?)]

Combined structural and textural inpainting[edit]

Combined structural and textural inpainting approaches simultaneously try to perform texture and structure filling in regions of missing image information. Most parts of an image consist of texture and structure. The boundaries between image regions accumulate structural information which is a complex phenomenon.[clarification needed (What does it mean that boundaries "accumulate information"?)] This is the result when blending different textures together. That is why, the state of the art inpainting method attempts to combine structural and textural inpainting.

A more traditional method is to use differential equations (such as the Laplace's equation) with Dirichlet boundary conditions for continuity (a seamless fit).[clarification needed (What is a Dirichlet boundary and how does it make something a seamless fit, and what is a seamless fit in this context?)] This works well if missing information lies within the homogeneous portion of an object area.[2]

Other methods follow isophote directions (in an image, a contour of equal luminance), to do the inpainting.[3] Recent investigations included the exploration of the wavelet transform properties to perform inpainting in the space-frequency domain, obtaining a better performance when compared to the frequency-based inpainting techniques.[4]

Model based inpainting follows the Bayesian approach for which missing information is best fitted or estimated from the combination of the models of the underlying images as well as the image data actually being observed. In deterministic language, this has led to various variational inpainting models.[clarification needed (Please rewrite this sentence in plain English.)][5]

Manual computer methods include using a clone tool or healing tool,[clarification needed (What is a healing tool?)] to copy existing parts of the image to restore a damaged texture. Texture synthesis may also be used.[6]

Exemplar-based image inpainting attempts to automate the clone tool process. It fills "holes" in the image by searching for similar patches in a nearby source region of the image, and copying the pixels from the most similar patch into the hole. By performing the fill at the patch level as opposed to the pixel level, the algorithm reduces blurring artifacts caused by prior techniques.[7][8]

See also[edit]

References[edit]

  1. ^ "This Researcher Created 'DeepCreamPy,' a Machine Learning Algorithm That Uncensors Hentai - Motherboard".
  2. ^ Peterson, Ivars (11 May 2002). "Filling in Blanks". Science News. 161 (19): 299–300. doi:10.2307/4013521. JSTOR 4013521. Retrieved 2008-05-11.
  3. ^ M. Bertalmío, G. Sapiro, V. Caselles and C. Ballester., "Image Inpainting", Proceedings of SIGGRAPH 2000, New Orleans, USA, July 2000.
  4. ^ Penedo, S. R. M.; Cipparrone, F. A. M.; Justo, J. F. (2019). "Digital Image Inpainting by Estimating Wavelet Coefficient Decays From Regularity Property and Besov Spaces". IEEE Access. 7: 3459–3471. doi:10.1109/ACCESS.2018.2882364.
  5. ^ T. F. Chan and J. Shen, "Mathematical Models for Local Nontexture Inpainting", SIAM J. Applied Math., 62(3), 2001, 1019-1043.
  6. ^ Image Replacement through Texture Synthesis, Homan Igehy and Lucas Pereira, Stanford University, Appears in the Proceedings of the 1997 IEEE International Conference on Image Processing
  7. ^ Object Removal by Exemplar-Based Inpainting, Criminisi, A, Perez, P., & Toyama, K., Appears in the Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  8. ^ Inpainting Strategies for Reconstruction of Missing Data in VHR Images, L. Lorenzi, F. Melgani and G. Mercier, IEEE Geoscience and Remote Sensing Letters, Set. 2011

External links[edit]

Retrieved from "https://en.wikipedia.org/w/index.php?title=Inpainting&oldid=878818551"