“Accelerating spatially varying Gaussian filters”
Conference:
Type(s):
Title:
- Accelerating spatially varying Gaussian filters
Session/Category Title: Sampling & filtering
Presenter(s)/Author(s):
Moderator(s):
Abstract:
High-dimensional Gaussian filters, most notably the bilateral filter, are important tools for many computer graphics and vision tasks. In recent years, a number of techniques for accelerating their evaluation have been developed by exploiting the separability of these Gaussians. However, these techniques do not apply to the more general class of spatially varying Gaussian filters, as they cannot be expressed as convolutions. These filters are useful because the underlying data—e.g. images, range data, meshes or light fields—often exhibit strong local anisotropy and scale. We propose an acceleration method for approximating spatially varying Gaussian filters using a set of spatially invariant Gaussian filters each of which is applied to a segment of some non-disjoint partitioning of the dataset. We then demonstrate that the resulting ability to locally tilt, rotate or scale the kernel improves filtering performance in various applications over traditional spatially invariant Gaussian filters, without incurring a significant penalty in computational expense.
References:
1. Adams, A., Gelfand, N., Dolson, J., and Levoy, M. 2009. Gaussian KD-trees for fast high-dimensional filtering. ACM Trans. on Graphics 28, 3 (Aug.), 21:1–21:12. Google ScholarDigital Library
2. Adams, A., Baek, J., and Davis, M. A. 2010. Fast high-dimensional filtering using the permutohedral lattice. In Proceedings of EUROGRAPHICS 2010, Eurographics, 753–762.Google Scholar
3. Buades, A., Coll, B., and Morel, J.-M. 2005. A non-local algorithm for image denoising. IEEE Conference on Computer Vision and Pattern Recognition 2, 60–65. Google ScholarDigital Library
4. Chen, J., Paris, S., and Durand, F. 2007. Real-time edge-aware image processing with the bilateral grid. ACM Trans. on Graphics 26 (July), 103:1–103:9. Google ScholarDigital Library
5. Choudhury, P., and Tumblin, J. 2003. The trilateral filter for high contrast images and meshes. Eurographics Symposium on Rendering, 186–196. Google ScholarDigital Library
6. Dolson, J., Baek, J., Plagemann, C., and Thrun, S. 2010. Upsampling range data in dynamic environments. IEEE Conference on Computer Vision and Pattern Recognition, 1141–1148.Google Scholar
7. Durand, F., and Dorsey, J. 2002. Fast bilateral filtering for the display of high-dynamic-range images. In Proceedings of SIGGRAPH 2002, ACM SIGGRAPH, ACM, 257–266. Google ScholarDigital Library
8. Eisemann, E., and Durand, F. 2004. Flash photography enhancement via intrinsic relighting. ACM Trans. on Graphics 23 (Aug.), 673–678. Google ScholarDigital Library
9. Fattal, R., Lischinski, D., and Werman, M. 2002. Gradient domain high dynamic range compression. In Proceedings of SIGGRAPH 2002, ACM SIGGRAPH, ACM, 249–256. Google ScholarDigital Library
10. Fleishman, S., Drori, I., and Cohen-Or, D. 2003. Bilateral mesh denoising. ACM Trans. on Graphics 22, 3 (July), 950–953. Google ScholarDigital Library
11. Genz, A. 2004. Numerical computation of rectangular bivariate and trivariate normal and t probabilities. Statistics and Computing 14, 151–160. Google ScholarDigital Library
12. Geusebroek, J.-M., and Smeulders, A. W. M. 2003. Fast anisotropic gauss filtering. IEEE Trans. on Image Processing 12, 8, 938–943. Google ScholarDigital Library
13. Granados, M., Ajdin, B., Wand, M., Theobalt, C., Seidel, H.-P., and Lensch, H. 2010. Optimal HDR reconstruction with linear digital cameras. IEEE Conference on Computer Vision and Pattern Recognition, 215–222.Google Scholar
14. Lam, S. Y. M., and Shi, B. E. 2007. Recursive anisotropic 2d gaussian filtering based on a triple-axis decomposition. IEEE Trans. on Image Processing 16, 7, 1925–1930.Google ScholarCross Ref
15. Lampert, C. H., and Wirjadi, O. 2006. An optimal nonorthogonal separation of the anisotropic gaussian convolution filter. IEEE Trans. on Image Processing 15, 11, 3502–3514. Google ScholarDigital Library
16. Larson, G. W., Rushmeier, H., and Piatko, C. 1997. A visibility matching tone reproduction operator for high dynamic range scenes. IEEE Trans. on Visualization and Computer Graphics 3, 291–306. Google ScholarDigital Library
17. Paris, S., and Durand, F. 2006. A fast approximation of the bilateral filter using a signal processing approach. In Proceedings of the European Conference on Computer Vision, 568–580. Google ScholarDigital Library
18. Paris, S., Kornprobst, P., Tumblin, J., and Durand, F. 2008. Bilateral filtering: Theory and applications. Computer Graphics and Vision, 1, 1–73.Google Scholar
19. Petschnigg, G., Szeliski, R., Agrawala, M., and Cohen, M. 2004. Digital photography with flash and no-flash image pairs. ACM Trans. on Graphics 23 (Aug.), 664–672. Google ScholarDigital Library
20. Shen, J., Fang, S., Zhao, H., Jin, X., and Sun, H. 2009. Fast approximation of trilateral filter for tone mapping using a signal processing approach. Signal Processing 89, 901–907. Google ScholarDigital Library
21. Tomasi, C., and Manduchi, R. 1998. Bilateral filtering for gray and color images. IEEE International Conference on Computer Vision, 836–846. Google ScholarDigital Library
22. Yang, Q., Yang, R., Davis, J., and Nistér, D. 2007. Spatial-depth super resolution for range images. IEEE Conference on Computer Vision and Pattern Recognition, 1–8.Google Scholar
23. Zhang, B., and Allebach, J. P. 2008. Adaptive bilateral filter for sharpness enhancement and noise removal. IEEE Trans. on Image Processing 17, 5, 664–678. Google ScholarDigital Library
