Skip to main content
SpringerLink
Log in

Perceptual Loss with Fully Convolutional for Image Residual Denoising

  • Conference paper
  • First Online:
Pattern Recognition (CCPR 2016)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 663))

Included in the following conference series:

Abstract

In this paper we propose a fully convolutional encoder-decoder framework for image residual transformation tasks. Instead of only using per-pixel loss function, the proposed framework learn end-to-end mapping combined with perceptual loss function that depend on low-level features from a pre-trained network. Pointing out the mapping function in order to handle noise-free image by introduce identity mapping. And through an analysis of the interplay between the neural networks and the underlying noisy distribution which they seeking to learn. We also show how to construct a uniform transform, which is then used to make a single deep neural network work well across different levels of noise. Comparing with previous approaches, ours achieves better performance. The experimental results indicate the efficiency of the proposed algorithm to cope with image denoising tasks.

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

References

  1. Agostinelli, F., Anderson, M.R., Lee, H.: Adaptive multi-column deep neural networks with application to robust image denoising. In: Advances in Neural Information Processing Systems, pp. 1493–1501 (2013)

    Google Scholar 

  2. Burger, H.C., Schuler, C.J., Harmeling, S.: Image denoising: can plain neural networks compete with BM3D? In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2392–2399. IEEE, June 2012

    Google Scholar 

  3. DabovK, F., KatkovnikV, K.O.E.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process. 16(8), 2080–2095 (2007)

    Article  MathSciNet  Google Scholar 

  4. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Li, F.F.: Imagenet: a large-scale hierarchical image database, pp. 248–255 (2009)

    Google Scholar 

  5. Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)

    Article  Google Scholar 

  6. Dosovitskiy, A., Brox, T.: Generating Images with Perceptual Similarity Metrics based on Deep Networks (2016)

    Google Scholar 

  7. Eigen, D., Krishnan, D., Fergus, R.: Restoring an image taken through a window covered with dirt or rain. In: 2013 IEEE International Conference on Computer Vision, pp. 633–640. IEEE, December 2013

    Google Scholar 

  8. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, vol. abs/1512.03385 (2016)

    Google Scholar 

  9. Hong, S., Noh, H., Han, B.: Decoupled deep neural network for semi-supervised semantic segmentation. In: Proceedings of Advances in Neural Information Processing System (2015)

    Google Scholar 

  10. Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)

    Article  Google Scholar 

  11. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift, Computer Science (2015)

    Google Scholar 

  12. Jain, V., Seung, S.: Natural Image Denoising with Convolutional Networks. In: Bottou, D.K., Schuurmans, D., Bengio, Y., L. (eds.) Advances in Neural Information Processing Systems, vol. 21, pp. 769–776. Curran Associates, Inc. (2009)

    Google Scholar 

  13. Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual Losses for Real-Time Style Transfer and Super-Resolution. arXiv Preprint, March 2016

    Google Scholar 

  14. Kingma, D., Ba, J.: Adam: a method for stochastic optimization. Eprint Arxiv (2014)

    Google Scholar 

  15. Li, H.M.: Deep learning for image denoising. Int. J. Signal Process. Image Process. Pattern Recogn. 7(3), 171–180 (2014)

    Google Scholar 

  16. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of IEEE Conference Computer Vision Pattern Recognition, pp. 3431–3440 (2015)

    Google Scholar 

  17. Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)

    Google Scholar 

  18. Mao, X.J., Shen, C., Yang, Y.B.: Image Denoising Using Very Deep Fully Convolutional Encoder-Decoder Networks with Symmetric Skip Connections. arXiv preprint, March 2016

    Google Scholar 

  19. Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of IEEE International Conference Computer Vision, pp. 1520–1528 (2015)

    Google Scholar 

  20. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)

    Google Scholar 

  21. Skribtsov, P.V., Surikov, S.O.: Regularization method for solving denoising and inpainting task using stacked sparse denoising autoencoders. Am. J. Appl. Sci. 13(1), 64–72 (2016)

    Article  Google Scholar 

  22. Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of International Conference Machine Learning, pp. 1096–1103 (2008)

    Google Scholar 

  23. Wang, X., Tao, Q., Wang, L., Li, D., Zhang, M.: Deep convolutional architecture for natural image denoising. In: 2015 International Conference on Wireless Communications & Signal Processing (WCSP), pp. 1–4. IEEE, October 2015

    Google Scholar 

  24. Wang, Y.Q., Morel, J.M.: Can a single image denoising neural network handle all levels of gaussian noise? IEEE Signal Process. Lett. 21(9), 1150–1153 (2014)

    Article  Google Scholar 

  25. Wu, Y., Zhao, H., Zhang, L.: Image denoising with rectified linear units. In: Loo, C.K., Yap, K.S., Wong, K.W., Beng Jin, A.T., Huang, K. (eds.) ICONIP 2014. LNCS, vol. 8836, pp. 142–149. Springer, Heidelberg (2014). doi:10.1007/978-3-319-12643-2_18

    Google Scholar 

  26. Xie, J., Xu, L., Chen, E.: Image denoising and inpainting with deep neural networks. In: Proceedings of Advances in Neural Information Processing System, pp. 350–358 (2012)

    Google Scholar 

  27. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Wavelets for Image Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)

    Article  Google Scholar 

  28. Zhang, L., Zhang, L., Mou, X., Zhang, D.: A comprehensive evaluation of full reference image quality assessment algorithms. In: 2012 19th IEEE International Conference on Image Processing, pp. 1477–1480. IEEE, September 2012

    Google Scholar 

  29. Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Is L2 a Good Loss Function for Neural Networks for Image Processing? arXiv preprint, November 2015

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu, 610041, China

    Tao Pan, Fu Zhongliang, Wang Lili & Zhu Kai

  2. University of Chinese Academy of Sciences, Beijing, 100049, China

    Tao Pan, Fu Zhongliang, Wang Lili & Zhu Kai

Authors
  1. Tao Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fu Zhongliang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wang Lili
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhu Kai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tao Pan .

Editor information

Editors and Affiliations

  1. Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Tieniu Tan

  2. Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, China

    Xuelong Li

  3. Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China

    Xilin Chen

  4. Tsinghua University , Beijing, China

    Jie Zhou

  5. Nanjing University of Science and Technology, Nanjing, China

    Jian Yang

  6. University of Electronic Science and Technology, Chengdu, Sichuan, China

    Hong Cheng

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer Nature Singapore Pte Ltd.

About this paper

Cite this paper

Pan, T., Zhongliang, F., Lili, W., Kai, Z. (2016). Perceptual Loss with Fully Convolutional for Image Residual Denoising. In: Tan, T., Li, X., Chen, X., Zhou, J., Yang, J., Cheng, H. (eds) Pattern Recognition. CCPR 2016. Communications in Computer and Information Science, vol 663. Springer, Singapore. https://doi.org/10.1007/978-981-10-3005-5_11

Download citation

  • DOI: https://doi.org/10.1007/978-981-10-3005-5_11

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-10-3004-8

  • Online ISBN: 978-981-10-3005-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation