Exemplar-based image inpainting: fast priority and coherent Nearest Neighbor search

Raul Martinez Noriega 1 Aline Roumy 1 Gilles Blanchard 2
1 Sirocco - Analysis representation, compression and communication of visual data
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : Greedy exemplar-based algorithms for inpainting face two main problems, decision of filling-in order and selection of \textit{good} exemplars from which the missing region is synthesized. We propose an algorithm that tackle these problems with improvements in the preservation of linear edges, and reduction of error propagation compared to well-known algorithms from the literature. Our improvement in the filling-in order is based on a combination of priority terms, previously defined by Criminisi, that better encourages the early synthesis of linear structures. The second contribution helps reducing the error propagation thanks to a better detection of outliers from the candidate patches carried. This is obtained with a new metric that incorporates the whole information of the candidate patches. Moreover, our proposal has significant lower computational load than most of the algorithms used for comparison in this paper.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-00752506
Contributor : Aline Roumy <>
Submitted on : Friday, November 16, 2012 - 5:33:24 AM
Last modification on : Wednesday, December 18, 2019 - 5:28:22 PM
Long-term archiving on: Sunday, February 17, 2013 - 3:55:16 AM

File

inpainting_mlsp12.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00752506, version 1

Citation

Raul Martinez Noriega, Aline Roumy, Gilles Blanchard. Exemplar-based image inpainting: fast priority and coherent Nearest Neighbor search. IEEE Workshop on Machine Learning for Signal Processing (MLSP), 2012, Santander, Spain. ⟨hal-00752506⟩

Share

Metrics

Record views

714

Files downloads

523