Skip to main content
SpringerLink
Log in

Learning Good Regions to Deblur Images

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

The goal of single image deblurring is to recover both a latent clear image and an underlying blur kernel from one input blurred image. Recent methods focus on exploiting natural image priors or additional image observations for deblurring, but pay less attention to the influence of image structure on estimating blur kernels. What is the useful image structure and how can one select good regions for deblurring? We formulate the problem of learning good regions for deblurring within the conditional random field framework. To better compare blur kernels, we develop an effective similarity metric for labeling training samples. The learned model is able to predict good regions from an input blurred image for deblurring without user guidance. Qualitative and quantitative evaluations demonstrate that good regions can be selected by the proposed algorithms for effective single image deblurring.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Notes

  1. Preliminary results of this work were presented in Hu and Yang (2012).

  2. Since the method (Bae et al. 2012) adopts a patch-mosaic framework to combine several patches and estimate the kernel from them, we directly use the results from their released code. We note that their deblurring formulation is similar to the algorithm (Shan et al. 2008).

References

  • Bae, H., Fowlkes, C. C., & Chou, P. H. (2012). Patch mosaic for fast motion deblurring. In Proceedings of Asian conference on computer vision (pp. 322–335).

  • Bardsley, J., Jefferies, S., Nagy, J., & Plemmons, R. (2006). A computational method for the restoration of images with an unknown, spatially-varying blur. Optics Express, 14(5), 1767–1782.

    Article  Google Scholar 

  • Ben-Ezra, M., & Nayar, S. (2003). Motion deblurring using hybrid imaging. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 657–664).

  • Besag, J. (2006). Statistical analysis of non-lattice data. Journal of the Royal Statistical Society: Series D, 24(3), 179–195.

    Google Scholar 

  • Cai, J., Ji, H., Liu, C., & Shen, Z. (2009). Blind motion deblurring from a single image using sparse approximation. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 104–111).

  • Cho, S., & Lee, S. (2009). Fast motion deblurring. In Proceedings of ACM SIGGRAPH Asia.

  • Cho., S., Matsushita, Y., & Lee, S. (2007). Removing non-uniform motion blur from images. In Proceedings of IEEE international conference on computer vision.

  • Cho, T. S., Joshi, N., Zitnick, C. L., Kang, S. B., Szeliski, R., & Freeman, W. T. (2010). A content-aware image prior. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 169–176).

  • Cho, T. S., Paris, S., Horn, B. K. P., & Freeman, W. T. (2011). Blur kernel estimation using the radon transform. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 241–248).

  • Fergus, R., Singh, B., Hertzmann, A., Roweis, S. T., & Freeman, W. T. (2006). Removing camera shake from a single photograph. In Proceedings of ACM SIGGRAPH (pp. 787–794).

  • Fletcher, R. (1970). A new approach to variable metric algorithms. The Computer Journal, 13(3), 317–322.

    Article  MATH  MathSciNet  Google Scholar 

  • Goldstein, A., & Fattal, R. (2012). Blur-kernel estimation from spectral irregularities. In Proceedings of European conference on computer vision (pp. 622–635).

  • Gupta, A., Joshi, N., Zitnick, L., Cohen, M., & Curless, B. (2010). Single image deblurring using motion density functions. In Proceedings of European conference on computer vision (pp. 171–184).

  • Hirsch, M., Schuler, C.J., Harmeling, S., & Schölkopf, B. (2011). Fast removal of non-uniform camera shake. In Proceedings of IEEE international conference on computer vision (pp. 463–470).

  • Hu, W., Xue, J., & Zheng, N. (2012). Psf estimation via gradient domain correlation. IEEE Transactions on Image Processing, 21(1), 386–392.

    Article  MathSciNet  Google Scholar 

  • Hu, Z., & Yang, M.H. (2012). Fast non-uniform deblurring using constrained camera pose subspace. In Proceedings of British machine vision conference.

  • Hu, Z., & Yang, M. H. (2012). Good regions to deblur. In Proceedings of European conference on computer vision (pp. 59–72).

  • Jia, J. (2007). Single image motion deblurring using transparency. In Proceedings of IEEE conference on computer vision and pattern recognition.

  • Joshi, N., Kang, S. B., Zitnick, C. L., & Szeliski, R. (2010). Image deblurring using inertial measurement sensors. In Proceedings of ACM SIGGRAPH (p. 30).

  • Joshi, N., Szeliski, R., & Kriegman, D. J. (2008). PSF estimation using sharp edge prediction. In Proceedings of IEEE conference on computer vision and pattern recognition.

  • Köhler, R., Hirsch, M., Mohler, B., Schölkopf, B., & Harmeling, S. (2012). Recording and playback of camera shake: Benchmarking blind deconvolution with a real-world database. In Proceedings of European conference on computer vision (pp. 27–40).

  • Krishnan, D., Tay, T., & Fergus, R. (2011). Blind deconvolution using a normalized sparsity measure. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 233–240).

  • Kumar, S., & Hebert, M. (2006). Discriminative random field. International Journal Computer Vision, 68(2), 179–201.

    Article  Google Scholar 

  • Lafferty, J., McCallum, A., & Pereira, F. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of international conference on machine learning (pp. 282–289).

  • Levin, A. (2006). Blind motion deblurring using image statistics. In Neural information processing systems (pp. 841–848).

  • Levin, A., Weiss, Y., Durand, F., & Freeman, W. T. (2009). Understanding and evaluating blind deconvolution algorithms. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 1964–1971).

  • Liu, S., Wang, H., Wang, J., Cho, S., & Pan, C. (2014). Automatic blur-kernel-size estimation for motion deblurring. The visual computer.

  • Raskar, R., Agrawal, A., & Tumblin, J. (2006). Coded exposure photography: Motion deblurring using fluttered shutter. In Proceedings of ACM SIGGRAPH (pp. 795–804).

  • Shan, Q., Jia, J., & Agarwala, A. (2008). High-quality motion deblurring from a single image. In Proceedings of ACM SIGGRAPH (pp. 73:1–73:10).

  • Shan, Q., Xiong, W., & Jia, J. (2007). Rotational motion deblurring of a rigid object from a single image. In Proceedings of IEEE international conference on computer vision.

  • Tai, Y., Tan, P., & Brown, M. S. (2011). Richardson-Lucy deblurring for scenes under projective motion path. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(8), 1603–1618.

    Article  Google Scholar 

  • Tai, Y. W., Du, H., Brown, M. S., & Lin, S. (2008). Image/video deblurring using a hybrid camera. In Proceedings of IEEE conference on computer vision and pattern recognition.

  • Whyte, O., Sivic, J., Zisserman, A., & Ponce, J. (2010). Non-uniform deblurring for shaken images. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 491–498).

  • Xu, L., & Jia, J. (2010). Two-phase kernel estimation for robust motion deblurring. In Proceedings of European conference on computer vision (pp. 157–170).

  • Xu, L., Zheng, S., & Jia, J. (2013). Unnatural l0 sparse representation for natural image deblurring. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 1107–1114).

  • Yedidia, J. S., Freeman, W. T., & Weiss, Y. (2003). Understanding belief propagation and its generalizations. In Exploring artificial intelligence in the new millennium (pp. 236–239). Morgan Kaufmann Publishers Inc.

  • Yitzhaky, Y., Mor, I., Lantzman, A., & Kopeika, N. (1998). Direct method for restoration of motion-blurred images. Journal of the Optical Society of America, 15(6), 1512–1519.

    Article  Google Scholar 

  • Yousaf, S., & Qin, S. Y. (2013). Blur kernel optimization: A new approach to patch selection with adaptive kernel estimation. Applied Mechanics and Materials, 436, 531–538.

    Article  Google Scholar 

  • Yuan, L., Sun, J., Quan, L., & Shum, H. (2007). Image deblurring with blurred/noisy image pairs. In Proceedings of ACM SIGGRAPH.

  • Zhong, L., Cho, T. S., Metaxas, D., Paris, S., & Wang, J. (2013). Handling noise in single image deblurring using directional filters. In Proceedings of IEEE conference on computer vision and pattern recognition.

Download references

Author information

Authors and Affiliations

  1. School of Engineering, University of California at Merced, Merced, CA, 95343, USA

    Zhe Hu & Ming-Hsuan Yang

Authors
  1. Zhe Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ming-Hsuan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ming-Hsuan Yang.

Additional information

Communicated by Cordelia Schmid.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1665 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hu, Z., Yang, MH. Learning Good Regions to Deblur Images. Int J Comput Vis 115, 345–362 (2015). https://doi.org/10.1007/s11263-015-0821-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-015-0821-1

Keywords

Search

Navigation