Home Journal of Computer Science and Technology Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Abstract
Keywords
Electronic Supplementary Material
References
Show full outline
Hide outline
Regular Paper

Fast and Error-Bounded Space-Variant Bilateral Filtering

National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
University of Chinese Academy of Sciences, Beijing 100049, China
School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094, China
State Key Laboratory of Remote Sensing Science, School of Geography, Beijing Normal University, Beijing 100875, China
Show Author Information

Abstract

The traditional space-invariant isotropic kernel utilized by a bilateral filter (BF) frequently leads to blurry edges and gradient reversal artifacts due to the existence of a large amount of outliers in the local averaging window. However, the efficient and accurate estimation of space-variant kernels which adapt to image structures, and the fast realization of the corresponding space-variant bilateral filtering are challenging problems. To address these problems, we present a space-variant BF (SVBF), and its linear time and error-bounded acceleration method. First, we accurately estimate spacevariant anisotropic kernels that vary with image structures in linear time through structure tensor and minimum spanning tree. Second, we perform SVBF in linear time using two error-bounded approximation methods, namely, low-rank tensor approximation via higher-order singular value decomposition and exponential sum approximation. Therefore, the proposed SVBF can efficiently achieve good edge-preserving results. We validate the advantages of the proposed filter in applications including: image denoising, image enhancement, and image focus editing. Experimental results demonstrate that our fast and error-bounded SVBF is superior to state-of-the-art methods.

Keywords

error-bounded accelerationedge-aware smoothingspace-variant bilateral filtering

Electronic Supplementary Material

Download File(s)
jcst-34-3-550-Highlights.pdf (741.6 KB)

References

[1]
Aurich V, Weule J. Non-linear Gaussian filters performing edge preserving diffusion. In Proc. the 1995 DAGMSymposium on Mustererkennung, September 1995, pp.538-545.
Crossref
[2]
Tomasi C, Manduchi R. Bilateral filtering for gray and color images. In Proc. the 6th International Conference on Computer Vision, January 1998, pp.839-846.
[3]

Zhang M, Gunturk B K. Multiresolution bilateral filtering for image denoising. IEEE Trans. Imge. Proc., 2008, 17(12): 2324-2333.

Crossref Google Scholar
[4]

Zhang B Y, Allebach J P. Adaptive bilateral filter for sharpness enhancement and noise removal. IEEE Trans. Imge. Proc., 2008, 17(5): 664-678.

Crossref Google Scholar
[5]

Durand F, Dorsey J. Fast bilateral filtering for the display of high-dynamic-range images. ACM Trans. Graphics, 2002, 21(3): 257-266.

Crossref Google Scholar
[6]

Yang Q X. Hardware-efficient bilateral filtering for stereo matching. IEEE Trans. Patt. Anal. Mach. Inte., 2014, 36(5): 1026-1032.

Crossref Google Scholar
[7]

He K M, Sun J, Tang X O. Guided image filtering. IEEE Trans. Patt. Anal. Mach. Inte., 2013, 35(6): 1397-1409.

Crossref Google Scholar
[8]
Choudhury P, Tumblin J. The trilateral filter for high contrast images and meshes. In Proc. the 2005 International Conference on Computer Graphics and Interactive Techniques, July 2005, Article No. 5.
Crossref
[9]
Porikli F. Constant time O(1) bilateral filtering. In Proc. the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 2008, Article No. 505.
Crossref
[10]

Chaudhury K N. Acceleration of the shiftable O(1) algorithm for bilateral filtering and nonlocal means. IEEE Trans. Imge. Proc., 2013, 22(4): 1291-1300.

Crossref Google Scholar
[11]

Dai L Q, Yuan M K, Zhang X P. Speeding up the bilateral filter: A joint acceleration way. IEEE Trans. Imge. Proc., 2016, 25(6): 2657-2672.

Crossref Google Scholar
[12]

Popkin T, Cavallaro A, Hands D. Accurate and efficient method for smoothly space-variant Gaussian blurring. IEEE Trans. Imge. Proc., 2010, 19(5): 1362-1370.

Crossref Google Scholar
[13]

Baek J, Jacobs D E. Accelerating spatially varying Gaussian filters. ACM Trans. Graphics, 2010, 29(6): Article No. 169.

Crossref Google Scholar
[14]

Muñoz-Barrutia A, Artaechevarria X, Ortiz-de-Solorzano C. Spatially variant convolution with scaled B-splines. IEEE Trans. Imge. Proc., 2010, 19(1): 11-24.

Crossref Google Scholar
[15]

Chaudhury K N, Mu˜noz-Barrutia A, Unser M. Fast spacevariant elliptical filtering using box splines. IEEE Trans. Imge. Proc., 2010, 19(9): 2290-2306.

Crossref Google Scholar
[16]

Bao L C, Song Y B, Yang Q X, Yuan H, Wang G. Tree filtering: Efficient structure-preserving smoothing with a minimum spanning tree. IEEE Trans. Imge. Proc., 2014, 23(2): 555-569.

Crossref Google Scholar
[17]

Zhang S, Sheng H, Li C, Zhang J, Xiong Z. Robust depth estimation for light field via spinning parallelogram operator. Computer Vision and Image Understanding, 2016, 145: 148-159.

Crossref Google Scholar
[18]

Sheng H, Zhang S, Cao X C, Fang Y J, Xiong Z. Geometric occlusion analysis in depth estimation using integral guided filter for light-field image. IEEE Trans. Imge. Proc., 2017, 26(12): 5758-5771.

Crossref Google Scholar
[19]
Shapiro L G, Stockman G C. Computer Vision: Theory and Applications, 2001.
[20]

Liu Q, Zhang C M, Guo Q, Zhou Y F. A nonlocal gradient concentration method for image smoothing. Computational Visual Media, 2015, 1(3): 197-209.

Crossref Google Scholar
[21]

Ma G H, Zhang M L, Li X M, Zhang C M. Image smoothing based on image decomposition and sparse high frequency gradient. Journal of Computer Science and Technology, 2018, 33(3): 502-510.

Crossref Google Scholar
[22]
Lu J B, Shi K Y, Min D B, Lin L, Do M N. Cross-based local multipoint filtering. In Proc. the 2012 IEEE Conference on Computer Vision and Pattern Recognition, June 2012, pp.430-437.
[23]
Tan X, Sun C M, Pham T D. Multipoint filtering with local polynomial approximation and range guidance. In Proc. the 2014 IEEE Conference on Computer Vision and Pattern Recognition, June 2014, pp.2941-2948.
Crossref
[24]
Dai L Q, Yuan M K, Zhang F H, Zhang X P. Fully connected guided image filtering. In Proc. the 2015 IEEE International Conference on Computer Vision, December 2015, pp.352-360.
Crossref
[25]

Gunturk B K. Fast bilateral filter with arbitrary range and domain kernels. IEEE Trans. Imge. Proc., 2011, 20(9): 2690-2696.

Crossref Google Scholar
[26]

Yuan M K, Zhang X P. Bilateral filter acceleration based on weighted variable projection. Electronics Letters, 2018, 54(6): 352-353.

Crossref Google Scholar
[27]

Getreuer P. A survey of Gaussian convolution algorithms. Image Processing on Line, 2013, 3: 286-310.

Crossref Google Scholar
[28]

Tan S, Dale J L, Johnston A. Performance of three recursive algorithms for fast space-variant Gaussian filtering. Real-Time Imaging, 2003, 9(3): 215-228.

Crossref Google Scholar
[29]
Xu L, Ren J, Yan Q, Liao R J, Jia J Y. Deep edge-aware filters. In Proc. the 32nd International Conference on Machine Learning, July 2015, pp.1669-1678.
[30]

Chen J W, Adams A, Wadhwa N, Hasinoff S W. Bilateral guided upsampling. ACM Trans. Graphics, 2016, 35(6): Article No. 203.

Crossref Google Scholar
[31]
Liu S F, Pan J S, Yang M H. Learning recursive filters for low-level vision via a hybrid neural network. In Proc. the 14th European Conference on Computer Vision, Part IV, October 2016, pp.560-576.
Crossref
[32]
Chen Q F, Xu J, Koltun V. Fast image processing with fully-convolutional networks. In Proc. the 2017 IEEE International Conference on Computer Vision, October 2017, pp.2516-2525.
Crossref
[33]
Wu H K, Zheng S, Zhang J G, Huang K Q. Fast end-to-end trainable guided filter. In Proc. the 2018 IEEE Conference on Computer Vision and Pattern Recognition, June 2018, pp.1838-1847.
Crossref
[34]
Xie J Y, Xu L L, Chen E H. Image denoising and inpainting with deep neural networks. In Proc. the 26th Annual Conference on Neural Information Processing Systems, December 2012, pp.350-358.
[35]
Meinhardt T, M¨oller M, Hazirbas C, Cremers D. Learning proximal operators: Using denoising networks for regularizing inverse imaging problems. In Proc. the 2017 IEEE International Conference on Computer Vision, October 2017, pp.1799-1808.
Crossref
[36]

Zhang K, Zuo W M, Chen Y J, Meng D Y, Zhang L. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Trans. Imge. Proc., 2017, 26(7): 3142-3155.

Crossref Google Scholar
[37]

Zhang K, Zuo W M, Zhang L. FFDNet: Toward a fast and flexible solution for CNN based image denoising. IEEE Trans. Imge. Proc., 2018, 27(9): 4608-4622.

Crossref Google Scholar
[38]
Lehtinen J, Munkberg J, Hasselgren J, Laine S, Karras T, Aittala M, Aila T. Noise2noise: Learning image restoration without clean data. arXiv: 1803.04189, 2018. https://arxiv.org/abs/1803.04189, March 2019.
[39]
Xu L, Ren J S J, Liu C, Jia J. Deep convolutional neural network for image deconvolution. In Proc. the 2014 Annual Conference on Neural Information Processing Systems, December 2014, pp.1790-1798.
[40]
Pan J S, Ren W Q, Hu Z, Yang M H. Learning to deblur images with exemplars. IEEE Trans. Patt. Anal. Mach. Inte. doi: 10.1109/TPAMI.2018.2832125.
Crossref
[41]
Shen Z Y, Lai W S, Xu T F, Kautz J, Yang M H. Deep semantic face deblurring. arXiv: 1803.03345, 2018. https://arxiv.org/abs/1803.03345, March 2019.
[42]
Kim J, Lee J K, Lee K M. Accurate image super-resolution using very deep convolutional networks. In Proc. the 2016 IEEE Conference on Computer Vision and Pattern Recognition, June 2016, pp.1646-1654.
Crossref
[43]

Dong C, Loy C C, He K M, Tang X O. Image superresolution using deep convolutional networks. IEEE Trans. Patt. Anal. Mach. Inte., 2016, 38(2): 295-307.

Crossref Google Scholar
[44]
Lai W S, Huang J B, Ahuja N, Yang M H. Fast and accurate image super-resolution with deep Laplacian pyramid networks. IEEE Trans. Patt. Anal. Mach. Inte. doi: 10.1109/TPAMI.2018.2865304.
Crossref
[45]

Lucas A, Iliadis M, Molina R, Katsaggelos A K. Using deep neural networks for inverse problems in imaging: Beyond analytical methods. IEEE Signal Processing Magazine, 2018, 35(1): 20-36.

Crossref Google Scholar
[46]
Wang Z, Bovik A C. Foveated image and video coding. In Digital Video, Image Quality and Perceptual Coding (1st edition), Wu H R, Rao K R (eds.), CRC Press, 2005, pp.431-457.
Crossref
[47]
Chaudhury K N. Optimally localized wavelets and smoothing kernels [Ph.D. Thesis]. Swiss Federal Institute of Technology Lausanne, 2011.
[48]
Bernad J. Digital Image Processing. Springer, 1997.
[49]
Deledalle C A, Denis L, Tabti S, Tupin F. Closed-form expressions of the eigen decomposition of 2 × 2 and 3 × 3 Hermitian matrices. Technical Report, Université de Lyon, 2017. https://hal.archives-ouvertes.fr/hal-01501-221/file/matrix_exp_and_log_formula.pdf, March 2019.
[50]

de Lathauwer L, de Moor B, Vandewalle J. A multilinear singular value decomposition. SIAM Journal on Matrix Analysis and Applications, 2000, 21(4): 1253-1278.

Crossref Google Scholar
[51]

Golub G, Pereyra V. Separable nonlinear least squares: The variable projection method and its applications. Inverse Problems, 2003, 19(2): Article No. R1.

Crossref Google Scholar
[52]

Beylkin G, Monzón L. On approximation of functions by exponential sums. Applied and Computational Harmonic Analysis, 2005, 19(1): 17-48.

Crossref Google Scholar
[53]
Deriche R. Recursively implementating the Gaussian and its derivatives. Technical Report, Institut National de Recherche en Informatique et en Automatique, 1993. https://hal.inria.fr/file/index/docid/74778/filename/RR-1893.pdf, March 2019.
[54]

Young I T, van Vliet L J. Recursive implementation of the Gaussian filter. Sign. Proc., 1995, 44(2): 139-151.

Crossref Google Scholar
[55]

Young I T, van Uliet L J, van Ginkel M. Recursive Gabor filtering. IEEE Trans. Sign. Proc., 2002, 50(11): 2798-2805.

Crossref Google Scholar
Journal of Computer Science and Technology
Volume 34 Issue 3,
May 2019
Pages 550-568
DOI: 10.1007/s11390-019-1926-8
Cite this article:
Yuan M-K, Dai L-Q, Yan D-M, et al. Fast and Error-Bounded Space-Variant Bilateral Filtering. Journal of Computer Science and Technology, 2019, 34(3): 550-568. https://doi.org/10.1007/s11390-019-1926-8
Metrics & Citations  
Article History
Copyright
Return