Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Scale-Covariant and Scale-Invariant Gaussian Derivative Networks Read chapter Read first chapter

2021 | OriginalPaper | Chapter

Synthetic Images as a Regularity Prior for Image Restoration Neural Networks

Authors : Raphaël Achddou, Yann Gousseau, Saïd Ladjal

Published in: Scale Space and Variational Methods in Computer Vision

Publisher: Springer International Publishing

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Deep neural networks have recently surpassed other image restoration methods which rely on hand-crafted priors. However, such networks usually require large databases and need to be retrained for each new modality. In this paper, we show that we can reach near-optimal performances by training them on a synthetic dataset made of realizations of a dead leaves model, both for image denoising and super-resolution. The simplicity of this model makes it possible to create large databases with only a few parameters. We also show that training a network with a mix of natural and synthetic images does not affect results on natural images while improving the results on dead leaves images, which are classically used for evaluating the preservation of textures. We thoroughly describe the image model and its implementation, before giving experimental results.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
previous chapter Variational Models for Signal Processing with Graph Neural Networks
next chapter Geometric Deformation on Objects: Unsupervised Image Manipulation via Conjugation
Literature
1.
Agustsson, E., Timofte, R.: Ntire 2017 challenge on single image super-resolution: dataset and study. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, July 2017
2.
Alvarez, L., Gousseau, Y., Morel, J.M.: The size of objects in natural and artificial images. In: Advances in Imaging and Electron Physics, vol. 111, pp. 167–242. Elsevier (1999)
3.
Bordenave, C., Gousseau, Y., Roueff, F.: The dead leaves model: a general tessellation modeling occlusion. Adv. Appl. Probab. 38(1), 31–46 (2006)MathSciNetCrossRef
4.
Buades, A., Coll, B., Morel, J.M.: A review of image denoising algorithms, with a new one. Multiscale Model. Simul. 4(2), 490–530 (2005)MathSciNetCrossRef
5.
6.
Cao, F., Guichard, F., Hornung, H.: Measuring texture sharpness of a digital camera. In: Digital Photography V, vol. 7250, p. 72500H. International Society for Optics and Photonics (2009)
7.
Cao, F., Guichard, F., Hornung, H.: Dead leaves model for measuring texture quality on a digital camera. In: Digital Photography VI, vol. 7537, p. 75370E. International Society for Optics and Photonics (2010)
8.
Chen, C., Chen, Q., Xu, J., Koltun, V.: Learning to see in the dark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3291–3300 (2018)
9.
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image restoration by sparse 3D transform-domain collaborative filtering. In: Astola, J.T., Egiazarian, K.O., Dougherty, E.R. (eds.) Image Processing: Algorithms and Systems VI, vol. 6812, pp. 62–73. International Society for Optics and Photonics, SPIE (2008). https://​doi.​org/​10.​1117/​12.​766355
10.
11.
Donoho, D.L., Johnstone, I.M., et al.: Minimax estimation via wavelet shrinkage. Ann. Stat. 26(3), 879–921 (1998)MathSciNetCrossRef
12.
Galerne, B., Gousseau, Y., Morel, J.M.: Micro-texture synthesis by phase randomization. Image Process. Line 1, 213–237 (2011)CrossRef
13.
14.
Gousseau, Y., Roueff, F.: Modeling occlusion and scaling in natural images. Multiscale Model. Simul. 6(1), 105–134 (2007)MathSciNetCrossRef
15.
Heeger, D.J., Bergen, J.R.: Pyramid-based texture analysis/synthesis. In: Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques, pp. 229–238 (1995)
16.
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
17.
Kendall, W.S., Thönnes, E.: Perfect simulation in stochastic geometry. Pattern Recogn. 32(9), 1569–1586 (1999)CrossRef
18.
Lee, A.B., Mumford, D., Huang, J.: Occlusion models for natural images: a statistical study of a scale-invariant dead leaves model. Int. J. Comput. Vis. 41(1–2), 35–59 (2001)CrossRef
19.
Ma, K., et al.: Waterloo exploration database: new challenges for image quality assessment models. IEEE Trans. Image Process. 26(2), 1004–1016 (2016)MathSciNetCrossRef
20.
21.
22.
Portilla, J., Simoncelli, E.P.: A parametric texture model based on joint statistics of complex wavelet coefficients. Int. J. Comput. Vis. 40(1), 49–70 (2000)CrossRef
23.
Prashnani, E., Cai, H., Mostofi, Y., Sen, P.: PieAPP: perceptual image-error assessment through pairwise preference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1808–1817 (2018)
24.
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D 60(1–4), 259–268 (1992)MathSciNetCrossRef
25.
Tassano, M., Delon, J., Veit, T.: An analysis and implementation of the FFDNet image denoising method. Image Process. Line 9, 1–25 (2019)CrossRef
26.
Tremblay, J., et al.: Training deep networks with synthetic data: bridging the reality gap by domain randomization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 969–977 (2018)
27.
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Deep image prior. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9446–9454 (2018)
28.
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRef
29.
Yu, G., Sapiro, G., Mallat, S.: Solving inverse problems with piecewise linear estimators: from gaussian mixture models to structured sparsity. IEEE Trans. Image Process. 21(5), 2481–2499 (2011)MathSciNetMATH
30.
Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26(7), 3142–3155 (2017)MathSciNetCrossRef
31.
Zhang, K., Zuo, W., Zhang, L.: FFDNet: toward a fast and flexible solution for CNN-based image denoising. IEEE Trans. Image Process. 27(9), 4608–4622 (2018)MathSciNetCrossRef
32.
Zhang, Y., Tian, Y., Kong, Y., Zhong, B., Fu, Y.: Residual dense network for image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2472–2481 (2018)
Metadata
Title
Synthetic Images as a Regularity Prior for Image Restoration Neural Networks
Authors
Raphaël Achddou
Yann Gousseau
Saïd Ladjal
Copyright Year
2021
Book
Scale Space and Variational Methods in Computer Vision

Print ISBN: 978-3-030-75548-5

Electronic ISBN: 978-3-030-75549-2

Copyright Year: 2021

DOI
https://doi.org/10.1007/978-3-030-75549-2_27

Premium Partner

    Image Credits