Skip to main content
SpringerLink
Log in

NAS-DIP: Learning Deep Image Prior with Neural Architecture Search

  • Conference paper
  • First Online:
Computer Vision – ECCV 2020 (ECCV 2020)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12363))

Included in the following conference series:

Abstract

Recent work has shown that the structure of deep convolutional neural networks can be used as a structured image prior for solving various inverse image restoration tasks. Instead of using hand-designed architectures, we propose to search for neural architectures that capture stronger image priors. Building upon a generic U-Net architecture, our core contribution lies in designing new search spaces for (1) an upsampling cell and (2) a pattern of cross-scale residual connections. We search for an improved network by leveraging an existing neural architecture search algorithm (using reinforcement learning with a recurrent neural network controller). We validate the effectiveness of our method via a wide variety of applications, including image restoration, dehazing, image-to-image translation, and matrix factorization. Extensive experimental results show that our algorithm performs favorably against state-of-the-art learning-free approaches and reaches competitive performance with existing learning-based methods in some cases.

Y.-C. Chen and C. Gao—Equal Contribution.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    We originally plan to conduct a quantitative evaluation using the O-HAZE dataset [4]. Unfortunately, using the provided source code and email correspondences with the authors, we were still unable to reproduce the results of DoubleDIP on this dataset. We thus did not report quantitative results on dehazing in this work.

References

  1. Agustsson, E., Timofte, R.: Ntire 2017 challenge on single image super-resolution: dataset and study. In: CVPRW (2017)

    Google Scholar 

  2. Ahmed, K., Torresani, L.: MaskConnect: connectivity learning by gradient descent. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 362–378. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_22

    Chapter  Google Scholar 

  3. Aittala, M., et al.: Computational mirrors: blind inverse light transport by deep matrix factorization. In: NeurIPS (2019)

    Google Scholar 

  4. Ancuti, C.O., Ancuti, C., Timofte, R., De Vleeschouwer, C.: O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images. In: CVPRW (2018)

    Google Scholar 

  5. Angeline, P.J., Saunders, G.M., Pollack, J.B.: An evolutionary algorithm that constructs recurrent neural networks. Trans. Neural Netw. 5, 54–65 (1994)

    Article  Google Scholar 

  6. Athar, S., Burnaev, E., Lempitsky, V.: Latent convolutional models. In: ICLR (2019)

    Google Scholar 

  7. Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. In: ICLR (2017)

    Google Scholar 

  8. Beck, A., Teboulle, M.: Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems. TIP 18, 2419–2434 (2009)

    MathSciNet  MATH  Google Scholar 

  9. Berthelot, D., Schumm, T., Metz, L.: Began: boundary equilibrium generative adversarial networks. arXiv (2017)

    Google Scholar 

  10. Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.L.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: BMVC (2012)

    Google Scholar 

  11. Bojanowski, P., Joulin, A., Lopez-Paz, D., Szlam, A.: Optimizing the latent space of generative networks. In: ICML (2018)

    Google Scholar 

  12. Burger, H.C., Schuler, C.J., Harmeling, S.: Image denoising: can plain neural networks compete with BM3D? In: CVPR (2012)

    Google Scholar 

  13. Cai, H., Chen, T., Zhang, W., Yu, Y., Wang, J.: Efficient architecture search by network transformation. In: AAAI (2018)

    Google Scholar 

  14. Chen, L.C., et al.: Searching for efficient multi-scale architectures for dense image prediction. In: NeurIPS (2018)

    Google Scholar 

  15. Chen, Y.C., Lin, Y.Y., Yang, M.H., Huang, J.B.: CrDoCo: pixel-level domain transfer with cross-domain consistency. In: CVPR (2019)

    Google Scholar 

  16. Cheng, Z., Gadelha, M., Maji, S., Sheldon, D.: A Bayesian perspective on the deep image prior. In: CVPR (2019)

    Google Scholar 

  17. Chu, X., Zhang, B., Ma, H., Xu, R., Li, J., Li, Q.: Fast, accurate and lightweight super-resolution with neural architecture search. arXiv (2019)

    Google Scholar 

  18. Dabov, K., Foi, A., Egiazarian, K.: Video denoising by sparse 3D transform-domain collaborative filtering. In: European Signal Processing Conference (2007)

    Google Scholar 

  19. Dai, T., Cai, J., Zhang, Y., Xia, S.T., Zhang, L.: Second-order attention network for single image super-resolution. In: CVPR (2019)

    Google Scholar 

  20. Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. TPAMI 38, 295–307 (2015)

    Article  Google Scholar 

  21. Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV (2015)

    Google Scholar 

  22. Gandelsman, Y., Shocher, A., Irani, M.: “Double-DIP”: unsupervised image decomposition via coupled deep-image-priors. In: CVPR (2019)

    Google Scholar 

  23. Gao, H., Wang, Z., Ji, S.: ChannelNets: compact and efficient convolutional neural networks via channel-wise convolutions. In: NeurIPS (2018)

    Google Scholar 

  24. Ghiasi, G., Lin, T.Y., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: CVPR (2019)

    Google Scholar 

  25. Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: ICCV (2009)

    Google Scholar 

  26. Gong, X., Chang, S., Jiang, Y., Wang, Z.: AutoGAN: neural architecture search for generative adversarial networks. In: ICCV (2019)

    Google Scholar 

  27. Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)

    Google Scholar 

  28. Guo, J., Li, Y., Lin, W., Chen, Y., Li, J.: Network decoupling: from regular to depthwise separable convolutions. In: BMVC (2018)

    Google Scholar 

  29. Guo, Y., Li, Y., Wang, L., Rosing, T.: Depthwise convolution is all you need for learning multiple visual domains. In: AAAI (2019)

    Google Scholar 

  30. He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: ICCV (2015)

    Google Scholar 

  31. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)

    Google Scholar 

  32. Heckel, R., Hand, P.: Deep decoder: Concise image representations from untrained non-convolutional networks. In: ICLR (2019)

    Google Scholar 

  33. Heide, F., Heidrich, W., Wetzstein, G.: Fast and flexible convolutional sparse coding. In: CVPR (2015)

    Google Scholar 

  34. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: NeurIPS (2017)

    Google Scholar 

  35. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR (2017)

    Google Scholar 

  36. Huang, J.B., Singh, A., Ahuja, N.: Single image super-resolution from transformed self-exemplars. In: CVPR (2015)

    Google Scholar 

  37. Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 179–196. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_11

    Chapter  Google Scholar 

  38. Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)

    Google Scholar 

  39. Jia, X., Chang, H., Tuytelaars, T.: Super-resolution with deep adaptive image resampling. arXiv (2017)

    Google Scholar 

  40. Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation. In: ICLR (2018)

    Google Scholar 

  41. Kim, J., Kwon Lee, J., Mu Lee, K.: Accurate image super-resolution using very deep convolutional networks. In: CVPR (2016)

    Google Scholar 

  42. Klambauer, G., Unterthiner, T., Mayr, A., Hochreiter, S.: Self-normalizing neural networks. In: NeurIPS (2017)

    Google Scholar 

  43. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NeurIPS (2012)

    Google Scholar 

  44. Lai, W.S., Huang, J.B., Ahuja, N., Yang, M.H.: Deep Laplacian pyramid networks for fast and accurate super-resolution. In: CVPR (2017)

    Google Scholar 

  45. Lai, W.S., Huang, J.B., Ahuja, N., Yang, M.H.: Fast and accurate image super-resolution with deep Laplacian pyramid networks. TPAMI 41, 2599–2613 (2018)

    Article  Google Scholar 

  46. Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR (2017)

    Google Scholar 

  47. Lee, H.-Y., Tseng, H.-Y., Huang, J.-B., Singh, M., Yang, M.-H.: Diverse image-to-image translation via disentangled representations. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 36–52. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_3

    Chapter  Google Scholar 

  48. Lee, H.-Y., et al.: DRIT++: diverse image-to-image translation via disentangled representations. Int. J. Comput. Vis. 128(10), 2402–2417 (2020). https://doi.org/10.1007/s11263-019-01284-z

    Article  Google Scholar 

  49. Lefkimmiatis, S.: Non-local color image denoising with convolutional neural networks. In: CVPR (2017)

    Google Scholar 

  50. Li, Y., Huang, J.-B., Ahuja, N., Yang, M.-H.: Deep joint image filtering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 154–169. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_10

    Chapter  Google Scholar 

  51. Lim, B., Son, S., Kim, H., Nah, S., Mu Lee, K.: Enhanced deep residual networks for single image super-resolution. In: CVPR (2017)

    Google Scholar 

  52. Liu, C., et al.: Auto-DeepLab: hierarchical neural architecture search for semantic image segmentation. In: CVPR (2019)

    Google Scholar 

  53. Liu, H., Simonyan, K., Vinyals, O., Fernando, C., Kavukcuoglu, K.: Hierarchial representations for efficient architecture search. In: ICLR (2018)

    Google Scholar 

  54. Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. In: ICLR (2019)

    Google Scholar 

  55. Liu, Y.L., Lai, W.S., Yang, M.H., Chuang, Y.Y., Huang, J.B.: Learning to see through obstructions. In: CVPR (2020)

    Google Scholar 

  56. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)

    Google Scholar 

  57. Luo, X., Huang, J., Szeliski, R., Matzen, K., Kopf, J.: Consistent video depth estimation. ACM Trans. Graph. (Proc. ACM SIGGRAPH) (2020)

    Google Scholar 

  58. Mataev, G., Milanfar, P., Elad, M.: DeepRED: deep image prior powered by red. In: ICCVW (2019)

    Google Scholar 

  59. Miikkulainen, R., et al.: Evolving deep neural networks. In: Artificial Intelligence in the Age of Neural Networks and Brain Computing (2019)

    Google Scholar 

  60. Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)

    Google Scholar 

  61. Nekrasov, V., Chen, H., Shen, C., Reid, I.: Fast neural architecture search of compact semantic segmentation models via auxiliary cells. In: CVPR (2019)

    Google Scholar 

  62. Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill 1, e3 (2016)

    Article  Google Scholar 

  63. Papyan, V., Romano, Y., Sulam, J., Elad, M.: Convolutional dictionary learning via local processing. In: ICCV (2017)

    Google Scholar 

  64. Qiu, Y., Wang, R., Tao, D., Cheng, J.: Embedded block residual network: a recursive restoration model for single-image super-resolution. In: ICCV (2019)

    Google Scholar 

  65. Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: ICML (2018)

    Google Scholar 

  66. Real, E., et al.: Large-scale evolution of image classifiers. In: ICML (2017)

    Google Scholar 

  67. Romano, Y., Elad, M., Milanfar, P.: The little engine that could: regularization by denoising (RED). SIAM J. Imaging Sci. 10, 1804–1844 (2017)

    Article  MathSciNet  Google Scholar 

  68. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  69. Saxe, A.M., Koh, P.W., Chen, Z., Bhand, M., Suresh, B., Ng, A.Y.: On random weights and unsupervised feature learning. In: ICML (2011)

    Google Scholar 

  70. Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: CVPR (2016)

    Google Scholar 

  71. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)

    Google Scholar 

  72. Stanley, K.O., D’Ambrosio, D.B., Gauci, J.: A hypercube-based encoding for evolving large-scale neural networks. Artif. Life 15, 185–212 (2009)

    Article  Google Scholar 

  73. Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10, 99–127 (2002)

    Article  Google Scholar 

  74. Suganuma, M., Ozay, M., Okatani, T.: Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search. In: ICML (2018)

    Google Scholar 

  75. Sun, Q., Ma, L., Joon Oh, S., Van Gool, L., Schiele, B., Fritz, M.: Natural and effective obfuscation by head inpainting. In: CVPR (2018)

    Google Scholar 

  76. Sun, Y., Wang, X., Liu, Z., Miller, J., Efros, A.A., Hardt, M.: Test-time training for out-of-distribution generalization. In: ICML (2020)

    Google Scholar 

  77. Tan, M., Chen, B., Pang, R., Vasudevan, V., Le, Q.V.: MnasNet: platform-aware neural architecture search for mobile. In: CVPR (2019)

    Google Scholar 

  78. Ulyanov, D., Vedaldi, A., Lempitsky, V.: Deep image prior. In: CVPR (2018)

    Google Scholar 

  79. Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C.C., Lin, D.: CARAFE: content-aware reassembly of features. In: ICCV (2019)

    Google Scholar 

  80. Wojna, Z., et al.: The devil is in the decoder: classification, regression and GANs. Int. J. Comput. Vis. 127(11), 1694–1706 (2019). https://doi.org/10.1007/s11263-019-01170-8

    Article  Google Scholar 

  81. Wojna, Z., et al.: The devil is in the decoder. In: BMVC (2017)

    Google Scholar 

  82. Xie, J., Xu, L., Chen, E.: Image denoising and inpainting with deep neural networks. In: NeurIPS (2012)

    Google Scholar 

  83. Xie, L., Yuille, A.: Genetic CNN. In: ICCV (2017)

    Google Scholar 

  84. Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. In: ICMLW (2015)

    Google Scholar 

  85. Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv (2015)

    Google Scholar 

  86. Zeiler, M.D., Taylor, G.W., Fergus, R.: Adaptive deconvolutional networks for mid and high level feature learning. In: ICCV (2011)

    Google Scholar 

  87. Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Boissonnat, J.-D., et al. (eds.) Curves and Surfaces 2010. LNCS, vol. 6920, pp. 711–730. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-27413-8_47

    Chapter  Google Scholar 

  88. Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 294–310. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_18

    Chapter  Google Scholar 

  89. Zhang, Y., Tian, Y., Kong, Y., Zhong, B., Fu, Y.: Residual dense network for image super-resolution. In: CVPR (2018)

    Google Scholar 

  90. Zhong, Z., Yan, J., Wu, W., Shao, J., Liu, C.L.: Practical block-wise neural network architecture generation. In: CVPR (2018)

    Google Scholar 

  91. Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)

    Google Scholar 

  92. Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: ICLR (2017)

    Google Scholar 

  93. Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: CVPR (2018)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Virginia Tech, Blacksburg, USA

    Yun-Chun Chen, Chen Gao, Esther Robb & Jia-Bin Huang

Authors
  1. Yun-Chun Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chen Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Esther Robb
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jia-Bin Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yun-Chun Chen .

Editor information

Editors and Affiliations

  1. University of Oxford, Oxford, UK

    Andrea Vedaldi

  2. Graz University of Technology, Graz, Austria

    Horst Bischof

  3. University of Freiburg, Freiburg im Breisgau, Germany

    Thomas Brox

  4. University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

    Jan-Michael Frahm

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (zip 88365 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chen, YC., Gao, C., Robb, E., Huang, JB. (2020). NAS-DIP: Learning Deep Image Prior with Neural Architecture Search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12363. Springer, Cham. https://doi.org/10.1007/978-3-030-58523-5_26

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-58523-5_26

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-58522-8

  • Online ISBN: 978-3-030-58523-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation