High-dimensional Guided Image Filtering

Shu Fujita, Norishige Fukushima

2016

Abstract

We present high-dimensional filtering for extending guided image filtering. Guided image filtering is one of edge-preserving filtering, and the computational time is constant to the size of the filtering kernel. The constant time property is essential for edge-preserving filtering. When the kernel radius is large, however, the guided image filtering suffers from noises because of violating a local linear model that is the key assumption in the guided image filtering. Unexpected noises and complex textures often violate the local linear model. Therefore, we propose high-dimensional guided image filtering to avoid the problems. Our experimental results show that our high-dimensional guided image filtering can work robustly and efficiently for various image processing.

References

  1. Adams, A., Baek, J., and Davis, M. A. (2010). Fast highdimensional filtering using the permutohedral lattice. Computer Graphics Forum, 29(2):753-762.
  2. Adams, A., Gelfand, N., Dolson, J., and Levoy, M. (2009). Gaussian kd-trees for fast high-dimensional filtering. ACM Trans. on Graphics, 28(3).
  3. Bae, S., Paris, S., and Durand, F. (2006). Two-scale tone management for photographic look. ACM Trans. on Graphics, 25(3):637-645.
  4. Buades, A., Coll, B., and Morel, J. M. (2005). A non-local algorithm for image denoising. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  5. Crow, F. C. (1984). Summed-area tables for texture mapping. In Proc. ACM SIGGRAPH, pages 207-212.
  6. Durand, F. and Dorsey, J. (2002). Fast bilateral filtering for the display of high-dynamic-range images. ACM Trans. on Graphics, 21(3):257-266.
  7. Eisemann, E. and Durand, F. (2004). Flash photography enhancement via intrinsic relighting. ACM Trans. on Graphics, 23(3):673-678.
  8. Fattal, R., Agrawala, M., and Rusinkiewicz, S. (2007). Multiscale shape and detail enhancement from multi-light image collections. ACM Trans. on Graphics, 26(3).
  9. Fujita, S., Fukushima, N., Kimura, M., and Ishibashi, Y. (2015). Randomized redundant dct: Efficient denoising by using random subsampling of dct patches. In Proc. ACM SIGGRAPH Asia Technical Briefs.
  10. Fukushima, N., Fujita, S., and Ishibashi, Y. (2015). Switching dual kernels for separable edge-preserving filtering. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
  11. Gastal, E. S. L. and Oliveira, M. M. (2011). Domain transform for edge-aware image and video processing. ACM Trans. on Graphics, 30(4).
  12. Gastal, E. S. L. and Oliveira, M. M. (2012). Adaptive manifolds for real-time high-dimensional filtering. ACM Trans. on Graphics, 31(4).
  13. He, K., Shun, J., and Tang, X. (2010). Guided image ffiltering. In Proc. European Conference on Computer Vision (ECCV).
  14. He, K., Sun, J., and Tang, X. (2009). Single image haze removal using dark channel prior. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  15. Hosni, A., Rhemann, C., Bleyer, M., Rother, C., and Gelautz, M. (2013). Fast cost-volume filtering for visual vorrespondence and beyond. IEEE Trans. on Pattern Analysis and Machine Intelligence, 35(2):504- 511.
  16. Kang, X., Li, S., and Benediktsson, J. (2014). Spectralspatial hyperspectral image classification with edgepreserving filtering. IEEE Trans. on Geoscience and Remote Sensing, 52(5):2666-2677.
  17. Kopf, J., Cohen, M., Lischinski, D., and Uyttendaele, M. (2007). Joint bilateral upsampling. ACM Trans. on Graphics, 26(3).
  18. Melgani, F. and Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans. on Geoscience and Remote Sensing, 42(8):1778-1790.
  19. Paris, S. and Durand, F. (2009). A fast approximation of the bilateral filter using a signal processing approach. International Journal of Computer Vision, 81(1):24- 52.
  20. Petschnigg, G., Agrawala, M., Hoppe, H., Szeliski, R., Cohen, M., and Toyama, K. (2004). Digital photography with flash and no-flash image pairs. ACM Trans. on Graphics, 23(3):664-672.
  21. Pham, T. Q. and Vliet, L. J. V. (2005). Separable bilateral filtering for fast video preprocessing. In Proc. IEEE International Conference on Multimedia and Expo (ICME).
  22. Porikli, F. (2008). Constant time o(1) bilateral filtering. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  23. Tasdizen, T. (2008). Principal components for non-local means image denoising. In Proc. IEEE International Conference on Image Processing (ICIP).
  24. Tomasi, C. and Manduchi, R. (1998). Bilateral filtering for gray and color images. In Proc. IEEE International Conference on Computer Vision (ICCV).
  25. Yang, Q. (2012). Recursive bilateral filtering. InProc. European Conference on Computer Vision (ECCV).
  26. Yang, Q., Tan, K. H., and Ahuja, N. (2009). Real-time o(1) bilateral filtering. InProc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Download


Paper Citation


in Harvard Style

Fujita S. and Fukushima N. (2016). High-dimensional Guided Image Filtering . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 25-32. DOI: 10.5220/0005715100250032


in Bibtex Style

@conference{visapp16,
author={Shu Fujita and Norishige Fukushima},
title={High-dimensional Guided Image Filtering},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={25-32},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005715100250032},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)
TI - High-dimensional Guided Image Filtering
SN - 978-989-758-175-5
AU - Fujita S.
AU - Fukushima N.
PY - 2016
SP - 25
EP - 32
DO - 10.5220/0005715100250032