Advertisement

6-DOF motion blur synthesis and performance evaluation of light field deblurring

  • Jonathan Samuel Lumentut
  • Williem
  • In Kyu ParkEmail author
Article
  • 18 Downloads

Abstract

Motion deblurring is essential for reconstructing sharp images from given a blurry input caused by the camera motion. The complexity of this problem increases in a light field due to its depth-dependent blur constraint. A method of generating synthetic 3 degree-of-freedom (3-DOF) translation blur on a light field image without camera rotation has been introduced. In this study, we generate a camera translation and rotation (6-DOF) motion blur model that preserves the consistency of the light field image. Our experiment results show that the proposed blur model can maintain the parallax information (depth-dependent blur) in a light field image. Furthermore, we produce a synthetic blurry light field dataset based on the 6-DOF model. Finally, to validate the usability of the synthetic dataset, we conduct extensive benchmarking using state-of-the-art motion deblurring algorithms.

Keywords

Light field 6-DOF Synthetic blur Motion blur Deblur 

Notes

Acknowledgment

This work was supported by Inha University Research Grant.

References

  1. 1.
    Bok Y, Jeon HG, Kweon IS (2017) Geometric calibration of micro-lense-based light field cameras using line features. IEEE Trans Pattern Anal Mach Intell 39 (2):287–300CrossRefGoogle Scholar
  2. 2.
    Chandramouli P, Jin M, Perrone D, Favaro P (2018) Plenoptic image motion deblurring. IEEE Trans Image Process 27(4):1723–1734MathSciNetCrossRefGoogle Scholar
  3. 3.
    Cho D, Lee M, Kim S, Tai YW (2013) Modeling the calibration pipeline of the lytro camera for high quality light-field image reconstruction. In: Proc of IEEE International Conference on Computer Vision, pp 3280–3287Google Scholar
  4. 4.
    Cho S, Lee S (2009) Fast motion deblurring. ACM Trans Graph (TOG) 28 (5):145CrossRefGoogle Scholar
  5. 5.
    Dansereau DG, Eriksson A, Leitner J (2017) Richardson-Lucy deblurring for moving light field cameras. In: Proc of IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp 70–81Google Scholar
  6. 6.
    Dansereau DG, Pizarro O, Williams SB (2013) Decoding, calibration and rectification for lenselet-based plenoptic cameras. InL Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp 1027–1034Google Scholar
  7. 7.
    Honauer K, Johannsen O, Kondermann D, Goldluecke B (2016) A dataset and evaluation methodology for depth estimation on 4D light fields. In: Asian Conference on Computer Vision, pp 19–34Google Scholar
  8. 8.
    Jin M, Chandramouli P, Favaro P (2015) Bilayer blind deconvolution with the light field camera. In: Proc of IEEE International Conference on Computer Vision Workshops, pp 10–18Google Scholar
  9. 9.
    Joshi N, Kang SB, Zitnick CL, Szeliski R (2010) Image deblurring using inertial measurement sensors. ACM Trans Graph 29(4):30CrossRefGoogle Scholar
  10. 10.
    Kalantari NK, Wang TC, Ramamoorthi R (2016) Learning-based view synthesis for light field cameras. ACM Transactions on Graphics 35(6):193Google Scholar
  11. 11.
    Köhler R, Hirsch M, Mohlder B, Schölkopf B, Harmeling S (2012) Recording and playback of camera shake: Benchmarking blind deconvolution with a real-world database. In: Proc of European Conference on Computer Vision, pp 27–40Google Scholar
  12. 12.
    Krishnan D, Tay T, Fergus R (2011) Blind deconvolution using a normalized sparsity measure. In: Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp 233—-240Google Scholar
  13. 13.
    Lai WS, Huang JB, Hu Z, Ahuja N, Yang MH (2016) A comparative study for single image blind deblurring. In: Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp 1701–1709Google Scholar
  14. 14.
    Lee D, Park H, Park IK, Lee KM (2018) Joint blind motion deblurring and depth estimation of light field. In: Proc of European Conference on Computer VisionGoogle Scholar
  15. 15.
    Levin A, Fergus R, Durand F, Freeman WT (2007) Image and depth from a conventional camera with a coded aperture. ACM Trans Graph 26(3):70CrossRefGoogle Scholar
  16. 16.
    Light field toolbox for Matlab v0.4. https://bit.ly/2JptsOT
  17. 17.
    Lytro. The Lytro camera. http://www.lytro.com/
  18. 18.
    Mahesh Mohan M, Rajagopalan A (2018) Divide and conquer for full-resolution light field deblurring. In: Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6421–6429Google Scholar
  19. 19.
    Pan J, Hu Z, Su Z, Yang MH (2014) Deblurring text images via L 0-regularized intensity and gradient prior. In: Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp 2901–2908Google Scholar
  20. 20.
    Pan J, Sun D, Pfister H, Yang MH (2016) Blind image deblurring using dark channel prior. In: Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp 1628–1636Google Scholar
  21. 21.
    Sellent A, Rother C, Roth S (2016) Stereo video deblurring. In: Proc of IEEE European Conference on Computer Vision, pp 558–575Google Scholar
  22. 22.
    Srinivasan PP, Ng R, Ramamoorthi R (2017) Light field blind motion deblurring. In: Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp 3958–3966Google Scholar
  23. 23.
    Srinivasan PP, Wang T, Sreelal A, Ng R (2017) Learning to synthesize a 4D RGBD light field from a single image. In: Proc of IEEE International Conference on Computer Vision, pp 2262–2270Google Scholar
  24. 24.
    Tai YW, Tan P, Brown MS (2011) Richardson-lucy deblurring for scenes under a projective motion path. IEEE Trans Pattern Anal Mach Intell 33(8):1603–1618CrossRefGoogle Scholar
  25. 25.
    The (New) Stanford Light Field Archive. http://lightfield.stanford.edu/lfs.html
  26. 26.
    Wang TC, Efros A, Ramamoorthi R (2016) Depth estimation with occlusion modeling using light-field cameras. IEEE Trans Pattern Anal Mach Intell 38 (11):2170–2181CrossRefGoogle Scholar
  27. 27.
    Whyte O, Sivic J, Zisserman A, Ponce J (2010) Non-uniform deblurring for shaken images. In: Proc of IEEE Conference on Computer Vision and Pattern Recognition, 2, pp 168–186Google Scholar
  28. 28.
    Whyte O, Sivic J, Zisserman A, Ponce J (2012) Non-uniform deblurring for shaken images. Int J Comput Vis 98:157–170MathSciNetCrossRefzbMATHGoogle Scholar
  29. 29.
    Williem W, Park IK, Lee KM (2018) Robust light field depth estimation using occlusion-noise aware data costs. IEEE Trans Pattern Anal Mach Intell 40(10):2484–2497CrossRefGoogle Scholar
  30. 30.
    Xu L, Jia J (2010) Two-phase kernel estimation for robust motion deblurring. In: Proc of European Conference on Computer Vision, pp 157–170Google Scholar
  31. 31.
    Xu L, Jia J (2012) Depth-aware motion deblurring. In: Proc of IEEE International Conference on Computational Photography, pp 1–8Google Scholar
  32. 32.
    Xu L, Zheng S, Jia J (2013) Unnatural L 0 sparse representation for natural image deblurring. In: Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp 1107–1114Google Scholar
  33. 33.
    Yan C, Li L, Zhang C, Liu B, Zhang Y, Dai Q (2019) Cross-modality bridging and knowledge transferring for image understanding. IEEE Trans on MultimediaGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department Information and Communication EngineeringInha UniversityIncheonKorea
  2. 2.Computer Science Department, School of Computer ScienceBina Nusantara UniversityJakartaIndonesia

Personalised recommendations