Object Removal by Exemplar-Based Inpainting

  title={Object Removal by Exemplar-Based Inpainting},
  author={Antonio Criminisi and Patrick P{\'e}rez and Kentaro Toyama},
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 generatinglarge image regions from sample textures, and (ii) “inpainting” techniques for filling insmall image gaps. The former work well for “textures” – repeating twodimensional patterns with some stochasticity; the… CONTINUE READING
Highly Influential
This paper has highly influenced 105 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 945 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 565 extracted citations

Multi Level Methods for Data Completion

Michal Holtzman Gazit
View 10 Excerpts
Highly Influenced

Image inpainting via sparse representation

2009 IEEE International Conference on Acoustics, Speech and Signal Processing • 2009
View 10 Excerpts
Highly Influenced

Detection of digital doctoring in exemplar-based inpainted images

2008 International Conference on Machine Learning and Cybernetics • 2008
View 11 Excerpts
Highly Influenced

Image-based façade modeling

ACM Trans. Graph. • 2008
View 4 Excerpts
Highly Influenced

Layered Scene Models from Single Hazy Images

IEEE Transactions on Visualization and Computer Graphics • 2018
View 5 Excerpts
Highly Influenced

Spatio-Temporal Disocclusion Filling Using Novel Sprite Cells

IEEE Transactions on Multimedia • 2018
View 9 Excerpts
Highly Influenced

Image Completion Using Sample Synthesis

2017 IEEE 31st International Conference on Advanced Information Networking and Applications (AINA) • 2017
View 9 Excerpts
Highly Influenced

Robust detection for object removal with post-processing by exemplar-based image inpainting

2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) • 2017
View 4 Excerpts
Highly Influenced

945 Citations

Citations per Year
Semantic Scholar estimates that this publication has 945 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 25 references

Similar Papers

Loading similar papers…