Advertisement

Weighted aggregation for guided image filtering

  • Bin Chen
  • Shiqian WuEmail author
Original Paper
  • 13 Downloads

Abstract

As a local filter, the guided image filtering (GIF) suffers from halo artifacts. To address this issue, a novel weighted aggregating strategy is proposed in this paper. By introducing the weighted aggregation to GIF, the proposed method called WAGIF can achieve results with sharp edges and avoid/reduce halo artifacts. More specifically, compared to the weighted guided image filtering and the gradient domain guided image filtering, the proposed method can achieve both fine and coarse smoothing results in the flat areas while preserving edges. In addition, the complexity of the proposed approach is O(N) for an image with N pixels. It is demonstrated that the GIF with weighted aggregation performs well in the fields of computational photography and image processing, including single image detail enhancement, tone mapping of high-dynamic-range images, single image haze removal, etc.

Keywords

Edge-preserving filtering Weighted aggregation Detail enhancement HDR tone mapping Haze removal 

Notes

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China under Grants 61775172 and 61371190. The authors wish to acknowledge the anonymous reviewers’ insightful and inspirational comments that have greatly helped to improve the technical contents and readability of this paper.

Supplementary material

11760_2019_1579_MOESM1_ESM.pdf (1.8 mb)
Supplementary material 1 (pdf 1833 KB)

References

  1. 1.
    Ali, S., Daul, C., Galbrun, E., Guillemin, F., Blondel, W.: Anisotropic motion estimation on edge preserving riesz wavelets for robust video mosaicing. Pattern Recognit. 51, 425–442 (2016).  https://doi.org/10.1016/j.patcog.2015.09.021 CrossRefGoogle Scholar
  2. 2.
    Choi, L.K., You, J., Bovik, A.C.: Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Trans. Image Process. 24(11), 3888–3901 (2015).  https://doi.org/10.1109/TIP.2015.2456502 MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Crow, F.C.: Summed-area tables for texture mapping. SIGGRAPH Comput. Graph. 18(3), 207–212 (1984).  https://doi.org/10.1145/964965.808600 CrossRefGoogle Scholar
  4. 4.
    Durand, F., Dorsey, J.: Fast bilateral filtering for the display of high-dynamic-range images. ACM Trans. Graph. 21(3), 257–266 (2002).  https://doi.org/10.1145/566654.566574 CrossRefGoogle Scholar
  5. 5.
    Farbman, Z., Fattal, R., Lischinski, D., Szeliski, R.: Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM Trans. Graph. 27(3), 1–10 (2008).  https://doi.org/10.1145/1360612.1360666 CrossRefGoogle Scholar
  6. 6.
    Fattal, R., Agrawala, M., Rusinkiewicz, S.: Multiscale shape and detail enhancement from multi-light image collections. ACM Trans. Graph. (2007).  https://doi.org/10.1145/1276377.1276441 CrossRefGoogle Scholar
  7. 7.
    Fattal, R., Lischinski, D., Werman, M.: Gradient domain high dynamic range compression. ACM Trans. Graph. 21(3), 249–256 (2002).  https://doi.org/10.1145/566654.566573 CrossRefGoogle Scholar
  8. 8.
    He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341–2353 (2011)CrossRefGoogle Scholar
  9. 9.
    He, K., Sun, J., Tang, X.: Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35(6), 1397–1409 (2013).  https://doi.org/10.1109/TPAMI.2012.213 CrossRefGoogle Scholar
  10. 10.
    Jiang, X., Yao, H., Liu, D.: Nighttime image enhancement based on image decomposition. Signal Image Video Process. 13(1), 189–197 (2019).  https://doi.org/10.1007/s11760-018-1345-2 CrossRefGoogle Scholar
  11. 11.
    Kim, B.K., Park, R.H., Chang, S.: Tone mapping with contrast preservation and lightness correction in high dynamic range imaging. Signal Image Video Process. 10(8), 1425–1432 (2016).  https://doi.org/10.1007/s11760-016-0942-1 CrossRefGoogle Scholar
  12. 12.
    Kou, F., Chen, W., Wen, C., Li, Z.: Gradient domain guided image filtering. IEEE Trans. Image Process. 24(11), 4528–4539 (2015).  https://doi.org/10.1109/TIP.2015.2468183 MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Li, X., Yan, Q., Yang, X., Jia, J.: Structure extraction from texture via relative total variation. ACM Trans. Graph. 31(6), 1–10 (2012)Google Scholar
  14. 14.
    Li, Y., Sharan, L., Adelson, E.H.: Compressing and companding high dynamic range images with subband architectures. ACM Trans. Graph. 24(3), 836–844 (2005).  https://doi.org/10.1145/1073204.1073271 CrossRefGoogle Scholar
  15. 15.
    Li, Z., Zheng, J., Zhu, Z., Yao, W., Wu, S.: Weighted guided image filtering. IEEE Trans. Image Process. 24(1), 120–129 (2015).  https://doi.org/10.1109/TIP.2014.2371234 MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Michailovich, O.V.: An iterative shrinkage approach to total-variation image restoration. IEEE Trans. Image Process. 20(5), 1281–1299 (2011).  https://doi.org/10.1109/TIP.2010.2090532 MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Min, D., Choi, S., Lu, J., Ham, B., Sohn, K., Do, M.N.: Fast global image smoothing based on weighted least squares. IEEE Trans. Image Process. 23(12), 5638–5653 (2014).  https://doi.org/10.1109/TIP.2014.2366600 MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Mun, J., Jang, Y., Kim, J.: Propagated guided image filtering for edge-preserving smoothing. Signal Image Video Process. 12(6), 1165–1172 (2018).  https://doi.org/10.1007/s11760-018-1268-y CrossRefGoogle Scholar
  19. 19.
    Oliveira, M.M.: Domain transform for edge-aware image and video processing. ACM Trans. Graph. 30(4), 1–12 (2011).  https://doi.org/10.1145/2010324.1964964 CrossRefGoogle Scholar
  20. 20.
    Paras, J., Vipin, T.: An adaptive edge-preserving image denoising technique using patch-based weighted-SVD filtering in wavelet domain. Multimed. Tools Appl. 76(2), 1659–1679 (2017).  https://doi.org/10.1007/s11042-015-3154-8 CrossRefGoogle Scholar
  21. 21.
    Pham, C.C., Ha, S.V.U., Jeon, J.W.: Adaptive guided image filtering for sharpness enhancement and noise reduction. In: Pacific Rim Conference on Advances in Image and Video Technology, pp. 323–334 (2011)Google Scholar
  22. 22.
    Porikli, F.: Constant time O(1) bilateral filtering. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008).  https://doi.org/10.1109/CVPR.2008.4587843
  23. 23.
    Ren, W., Liu, S., Ma, L., Xu, Q., Xu, X., Cao, X., Du, J., Yang, M.: Low-light image enhancement via a deep hybrid network. IEEE Trans. Image Process. 28(9), 4364–4375 (2019).  https://doi.org/10.1109/TIP.2019.2910412 MathSciNetCrossRefGoogle Scholar
  24. 24.
    Ren, W., Ma, L., Zhang, J., Pan, J., Cao, X., Liu, W., Yang, M.: Gated fusion network for single image dehazing. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3253–3261 (2018).  https://doi.org/10.1109/CVPR.2018.00343
  25. 25.
    Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: IEEE International Conference on Computer Vision, pp. 839–846 (1998).  https://doi.org/10.1109/ICCV.1998.710815
  26. 26.
    Xu, L., Lu, C., Xu, Y., Jia, J.: Image smoothing via \(L_0\) gradient minimization. ACM Trans. Graph. 30(6), 1–12 (2011).  https://doi.org/10.1145/2070781.2024208 Google Scholar
  27. 27.
    You, X., Du, L., Cheung, Y., Chen, Q.: A blind watermarking scheme using new nontensor product wavelet filter banks. IEEE Trans. Image Process. 19(12), 3271–3284 (2010).  https://doi.org/10.1109/TIP.2010.2055570 MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Institute of Robotics and Intelligent Systems, School of Information Science and EngineeringWuhan University of Science and TechnologyWuhanChina
  2. 2.Institute of Robotics and Intelligent Systems, School of Information Science and Engineering, Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial SystemsWuhan University of Science and TechnologyWuhanChina

Personalised recommendations