Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 1, pp 47–74 | Cite as

Iterative range-domain weighted filter for structural preserving image smoothing and de-noising

  • Lijun Zhao
  • Huihui BaiEmail author
  • Anhong Wang
  • Yao Zhao
Article
  • 215 Downloads

Abstract

The filtering weights from both spatial domain and range domain in the bilateral filtering always restrict filtering output value highly related to very close neighboring pixels, which results in very small changes before and after filtering. In order to better resolve the problem of piece-wise smoothness image’s de-noising, such as artifact removal of compressed depth image, we firstly propose an iterative range-domain weighted filter method. The filtering weights of the proposed method are calculated within a fixed window in an iterative way according to both pixel similarity in the range domain and image’s pixel occurring frequency, but there is no filtering weight from the spatial domain. Secondly, the proposed method is combined with Gaussian filtering as an engine in order to finish the task of image smoothing, because image smoothing for extracting structures is often sensitive to image’s fine details with strong gradients during suppressing image’s textures. To demonstrate the efficiency, we have applied the proposed method into many applications. For example, the proposed method has better performances on compressed depth artifact removal than BF, CVBF, and ADTF. Meanwhile, the proposed method is used for capture-noise removal of depth image. Additionally, the proposed method performs better performance on structural information preservation for image smoothing, as compared to several existing methods.

Keywords

Artifact removal Compression distortion Depth image Piece-wise smoothness image De-noising Image smoothing 

Notes

Acknowledgements

This work was supported in part by This work was supported in part by National Natural Science Foundation of China (No. 61672087, 61402033, 61672373) and the Fundamental Research Funds for the Central Universities.

References

  1. 1.
    Barash D, Comaniciu D (2004) A common framework for nonlinear diffusion, adaptive smoothing, bilateral filtering and mean shift. Image Vis Comput 22 (1):73–81.  https://doi.org/10.1016/j.imavis.2003.08.005 CrossRefGoogle Scholar
  2. 2.
    Comaniciu D, Peter M (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24(5):603–619.  https://doi.org/10.1109/34.1000236 CrossRefGoogle Scholar
  3. 3.
    Dabov K, Foi A, Egiazarian K (2006) Image denoising with block-matching and 3d filtering, In: proceedings SPIE 6064, image processing: algorithms and systems, neural networks, and machine learning, 606414.  https://doi.org/10.1117/12.643267
  4. 4.
    Electronic Telecommunication Res Institute (ETRI) and Gwangju Institute of Science and Technology (GIST) Korea, (2008) 3DV sequence of ETRI and GIST, ftp://203.253.130.48
  5. 5.
    Farbman Z, Fattal R, Lischinski D, Szeliski R (2008) Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM Trans Graph 27:3.  https://doi.org/10.1145/1360612.1360666 CrossRefGoogle Scholar
  6. 6.
    Fraunhofer Heinrich Hertz Inst Berlin, Germany (2013) 3DV sequence of HHI. ftp://hhi.de/HHIMPEG3DV/
  7. 7.
    Ham B, Cho M, Ponce J (2017) Robust guided image filtering using nonconvex potentials. IEEE Trans Pattern Anal Mach Intell PP(99):1–1.  https://doi.org/10.1109/TPAMI.2017.2669034 CrossRefGoogle Scholar
  8. 8.
    He K, Sun J, Tang X (2013) Guided image filtering. IEEE Trans Pattern Anal Mach Intell 35(6):1397–1409.  https://doi.org/10.1109/TPAMI.2012.213 CrossRefGoogle Scholar
  9. 9.
    Hu W, Li X, Cheung G, Au O (2013) Depth map denoising using graph-based transform and group sparsity. In: IEEE International workshop on multimedia signal processing, Italy.  https://doi.org/10.1109/MMSP.2013.6659254
  10. 10.
    ISO/IEC/JTC1/SC29/WG11/MPEG2011/N12036, Geneva Switzerland (2011) Call for proposals on 3D video coding technology (VQEG_3DTV_2011_022_MPEG w12036(3DV CfP)FINAL.doc). ftp://vqeg.its.bldrdoc.gov/Documents/VQEG_Seoul_Jun11/MeetingFiles/3DTV/
  11. 11.
    Karacan L, Erdem E, Erdem A (2013) Structure-preserving image smoothing via region covariances. ACM Trans Graph 32(6):176.  https://doi.org/10.1145/2508363.2508403 CrossRefGoogle Scholar
  12. 12.
    Kopf J, Cohen M, Lischinski D, Uyttendaele M (2007) Joint bilateral upsampling. ACM Trans Graph 26:3.  https://doi.org/10.1145/1276377.1276497 CrossRefGoogle Scholar
  13. 13.
    Kornprobst P, Tumblin J, Durand F (2008) Bilateral filtering: theory and applications, foundations and trends®;. Comput Graph Vis 4(1):1–73.  https://doi.org/10.1561/0600000020 CrossRefzbMATHGoogle Scholar
  14. 14.
    Liu S, Lai P, Tian D, Chen C (2011) New depth coding techniques with utilization of corresponding video. IEEE Trans Broadcast 57(2):551–561.  https://doi.org/10.1109/TBC.2011.2120750 CrossRefGoogle Scholar
  15. 15.
    Lu S, Ren X, Liu F (2014) Depth enhancement via low-rank matrix completion. In: IEEE Conference on computer vision and pattern recognition, Columbus, USA.  https://doi.org/10.1109/CVPR.2014.433
  16. 16.
    Min D, Lu J, Do M (2012) Depth video enhancement based on weighted mode filtering. IEEE Trans Image Process 21(3):1176–1190.  https://doi.org/10.1109/TIP.2011.2163164 MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Min D, Choi S, Lu J, Ham B, Sohn K, Do M (2014) Fast global image smoothing based on weighted least squares. IEEE Trans Image Process 23(12):5638–5653.  https://doi.org/10.1109/TIP.2014.2366600 MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Nagoya University Japan. 3DV sequence of Nagoya University, http://www.tanimoto.nuee.nagoya-u.ac.jp/MPEG-FTVProject.html
  19. 19.
    Nokia, Finnland. 3DV sequence of Nokia, http://mpeg3dv.nokiaresearch.com/sequence.html
  20. 20.
    Nowak R, Robert D (1999) Wavelet-based Rician noise removal for magnetic resonance imaging. IEEE Trans Image Process 8(10):1408–1419.  https://doi.org/10.1109/83.791966 CrossRefGoogle Scholar
  21. 21.
    Richardt C, Stoll C, Dodgson N, Seidel H, Theobalt C (2012) Coherent spatio-temporal filtering, upsampling and rendering of rgbz videos. Comp Graph Forum 31(2):247–256.  https://doi.org/10.1109/83.791966 CrossRefGoogle Scholar
  22. 22.
    Shen G, Kim W, Narang S, Ortegaand A, Lee J, Wey H (2011) Edge-adaptive transforms for efficient depth map coding, picture coding symposium, Nagoya, Japan, pp 566–569.  https://doi.org/10.1109/PCS.2010.5702565
  23. 23.
    Sutton C, McCallum A (2011) An introduction to conditional random fields. J Found Trends Mach Learn 4(4):267–373.  https://doi.org/10.1561/2200000013 CrossRefzbMATHGoogle Scholar
  24. 24.
    Tomasi C, Manduchi R (1998) Bilateral filtering for gray and color images. In: International conference on computer vision, Bombay, India, pp 839–846.  https://doi.org/10.1109/ICCV.1998.710815
  25. 25.
    Wang Z, Bovik A, Sheikh H, Simoncelli E (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612.  https://doi.org/10.1109/TIP.2003.819861 CrossRefGoogle Scholar
  26. 26.
    Weijer J, Boomgaard R (2001) Local mode filtering. In: IEEE Conference on computer vision and pattern recognition, pp II–428–II–433. Kauai, USA.  https://doi.org/10.1109/CVPR.2001.990993
  27. 27.
    Xu L, Lu C, Xu Y, Jia J (2011) Image smoothing via l0 gradient minimization. ACM Trans Graph 30(6):174.  https://doi.org/10.1145/2024156.2024208 CrossRefGoogle Scholar
  28. 28.
    Xu L, Yan Q, Xia Y, Jia J (2012) Structure extraction from texture via relative total variation. ACM Trans Graph 31(6):139.  https://doi.org/10.1145/2366145.2366158 CrossRefGoogle Scholar
  29. 29.
    Xu X, Po L, Cheung C, Cheung K, Feng L, Ting C, Ng K (2014) Adaptive depth truncation filter for mvc based compressed depth image. Signal Process Image Commun 29(3):316–331.  https://doi.org/10.1016/j.image.2013.12.005 CrossRefGoogle Scholar
  30. 30.
    Zhang Q, Xu L, Jia J (2014) Rolling guidance filter. In: European conference on computer vision, Zurich.  https://doi.org/10.1007/978-3-319-10578-9_53
  31. 31.
    Zhao L, Wang A, Zeng B, Wu Y (2015) Candidate value-based boundary filtering for compressed depth images. Electron Lett 51(3):224–226.  https://doi.org/10.1049/el.2014.3912 CrossRefGoogle Scholar
  32. 32.
    Zhao L, Bai H, Wang A, Zhao Y (2016) Joint iterative guidance filtering for compressed depth images, Visual Communications and Image Processing (VCIP), Chengdu, China, pp 1–4.  https://doi.org/10.1109/VCIP.2016.7805457
  33. 33.
    Zhao L, Bai H, Wang A, Zhao Y, Zeng B (2017) Two-stage filtering of compressed depth images with Markov random field. Signal Process Image Commun 54:11–22.  https://doi.org/10.1016/j.image.2017.02.009 CrossRefGoogle Scholar
  34. 34.
    Zhao L, Liang J, Bai H, Meng L, Wang A, Zhao Y (2017) Local activity-tuned image filtering for noise removal and image smoothing. Subject: Computer Vision and Pattern Recognition. arXiv:http://arXiv.org/abs/1707.02637

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  1. 1.Institute Information ScienceBeijing Jiaotong UniversityBeijingChina
  2. 2.Institute of Digital Media and CommunicationTaiyuan University of Science and TechnologyTaiyuanChina

Personalised recommendations