Advanced search
1 file | 2.28 MB Add to list
Author
Organization
Abstract
In this paper, we propose an efficient method for learning local image descriptors suitable for the use in image inpainting algorithms. We learn the descriptors using a convolutional autoencoder network that we design such that the network produces a computationally efficient extraction of patch descriptors through an intermediate image representation. This approach saves computational memory and time in comparison to existing methods when used with algorithms that require patch search and matching within a single image. We show these benefits by integrating our descriptor into an inpainting algorithm and comparing it to the existing autoencoder-based descriptor. We also show results indicating that our descriptor improves the robustness to missing areas of the patches.
Keywords
Local image descriptors, Patch descriptors, Autoencoders, Unsupervised deep learning, Inpainting

Downloads

  • paper120.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 2.28 MB

Citation

Please use this url to cite or link to this publication:

MLA
Žižakić, Nina, et al. “Autoencoder-Learned Local Image Descriptor for Image Inpainting.” Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019), edited by Katrien Beuls et al., vol. 2491, 2019.
APA
Žižakić, N., Ito, I., Meeus, L., & Pizurica, A. (2019). Autoencoder-learned local image descriptor for image inpainting. In K. Beuls, B. Bogaerts, G. Bontempi, P. Geurts, N. Harley, B. Lebichot, … P. Van Eecke (Eds.), Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019) (Vol. 2491). Brussels, Belgium.
Chicago author-date
Žižakić, Nina, Izumi Ito, Laurens Meeus, and Aleksandra Pizurica. 2019. “Autoencoder-Learned Local Image Descriptor for Image Inpainting.” In Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019), edited by Katrien Beuls, Bart Bogaerts, Gianluca Bontempi, Pierre Geurts, Nick Harley, Bertrand Lebichot, Tom Lenaerts, Gilles Louppe, and Paul Van Eecke. Vol. 2491.
Chicago author-date (all authors)
Žižakić, Nina, Izumi Ito, Laurens Meeus, and Aleksandra Pizurica. 2019. “Autoencoder-Learned Local Image Descriptor for Image Inpainting.” In Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019), ed by. Katrien Beuls, Bart Bogaerts, Gianluca Bontempi, Pierre Geurts, Nick Harley, Bertrand Lebichot, Tom Lenaerts, Gilles Louppe, and Paul Van Eecke. Vol. 2491.
Vancouver
1.
Žižakić N, Ito I, Meeus L, Pizurica A. Autoencoder-learned local image descriptor for image inpainting. In: Beuls K, Bogaerts B, Bontempi G, Geurts P, Harley N, Lebichot B, et al., editors. Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019). 2019.
IEEE
[1]
N. Žižakić, I. Ito, L. Meeus, and A. Pizurica, “Autoencoder-learned local image descriptor for image inpainting,” in Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019), Brussels, Belgium, 2019, vol. 2491.
@inproceedings{8636035,
  abstract     = {In this paper, we propose an efficient method for learning local image descriptors suitable for the use in image inpainting algorithms. We learn the descriptors using a convolutional autoencoder network that we design such that the network produces a computationally efficient extraction of patch descriptors through an intermediate image representation. This approach saves computational memory and time in comparison to existing methods when used with algorithms that require patch search and matching within a single image. We show these benefits by integrating our descriptor into an inpainting algorithm and comparing it to the existing autoencoder-based descriptor. 
We also show results indicating that our descriptor improves the robustness to missing areas of the patches.},
  articleno    = {120},
  author       = {Žižakić, Nina and Ito, Izumi and Meeus, Laurens and Pizurica, Aleksandra},
  booktitle    = {Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019)},
  editor       = {Beuls, Katrien and Bogaerts, Bart and Bontempi, Gianluca and Geurts, Pierre and Harley, Nick and Lebichot, Bertrand and Lenaerts, Tom and Louppe, Gilles and Van Eecke, Paul},
  issn         = {1613-0073},
  keywords     = {Local image descriptors,Patch descriptors,Autoencoders,Unsupervised deep learning,Inpainting},
  language     = {eng},
  location     = {Brussels, Belgium},
  pages        = {11},
  title        = {Autoencoder-learned local image descriptor for image inpainting},
  url          = {http://ceur-ws.org/Vol-2491/paper120.pdf},
  volume       = {2491},
  year         = {2019},
}