Abstract
Multiscale manipulations are central to image editing but also prone to halos. Achieving artifact-free results requires sophisticated edge-aware techniques and careful parameter tuning. These shortcomings were recently addressed by the local Laplacian filters, which can achieve a broad range of effects using standard Laplacian pyramids. However, these filters are slow to evaluate and their relationship to other approaches is unclear. In this article, we show that they are closely related to anisotropic diffusion and to bilateral filtering. Our study also leads to a variant of the bilateral filter that produces cleaner edges while retaining its speed. Building upon this result, we describe an acceleration scheme for local Laplacian filters on gray-scale images that yields speedups on the order of 50×. Finally, we demonstrate how to use local Laplacian filters to alter the distribution of gradients in an image. We illustrate this property with a robust algorithm for photographic style transfer.
Supplemental Material
- A. Adams, J. Baek, and A. Davis. 2010. Fast high-dimensional filtering using the permutohedral lattice. http://graphics.stanford.edu/papers/permutohedral/permutohedral.pdf.Google Scholar
- A. Adams, N. Gelfand, J. Dolson, and M. Levoy. 2009. Gaussian kd-trees for fast high-dimensional filtering. ACM Trans. Graph. 28, 3. Google ScholarDigital Library
- G. Aubert and P. Kornprobst. 2002. Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations. Applied Mathematical Sciences, vol. 147, Springer. Google ScholarDigital Library
- S. Bae, S. Paris, and F. Durand. 2006. Two-scale tone management for photographic look. ACM Trans. Graph. 25, 3, 637--645. Google ScholarDigital Library
- D. Barash and D. Comaniciu. 2004. A common framework for nonlinear diffusion, adaptive smoothing, bilateral filtering and mean shift. J. Image Video Comput. 22, 73--81.Google ScholarCross Ref
- M. J. Black, G. Sapiro, D. H. Marimont, and D. Heeger. 1998. Robust anisotropic diffusion. IEEE Trans. Image Process. 7, 3, 421--432. Google ScholarDigital Library
- A. Buades, B. Coll, and J.-M. Morel. 2005a. Neighborhood filters and PDE's. Tech. rep. 2005-04, CMLA.Google Scholar
- A. Buades, B. Coll, and J.-M. Morel. 2005b. A non-local algorithm for image denoising. In Proceedings of the Conference on Computer Vision and Pattern Recognition. Google ScholarDigital Library
- A. Buades, B. Coll, and J.-M. Morel. 2006. The staircasing effect in neighborhood filters and its solution. IEEE Trans. Image Process. 15, 6, 1499--1505. Google ScholarDigital Library
- J. Chen, S. Paris, and F. Durand. 2007. Real-time edge-aware image processing with the bilateral grid. ACM Trans. Graph. 26, 3. Google ScholarDigital Library
- K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian. 2006. Image denoising with block-matching and 3D filtering. Proc. SPIE 6064, A30.Google Scholar
- F. Durand and J. Dorsey. 2002. Fast bilateral filtering for the display of high-dynamic-range images. ACM Trans. Graph. 21, 3. Google ScholarDigital Library
- E. Eisemann and F. Durand. 2004. Flash photography enhancement via intrinsic relighting. ACM Trans. Graph. 23, 3. Google ScholarDigital Library
- M. Elad. 2002. On the bilateral filter and ways to improve it. IEEE Trans. Image Process. 11, 10. Google ScholarDigital Library
- Z. Farbman, R. Fattal, D. Lischinski, and R. Szeliski. 2008. Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM Trans. Graph. 27, 3. Google ScholarDigital Library
- R. Fattal. 2009. Edge-avoiding wavelets and their applications. ACM Trans. Graph. 28, 3. Google ScholarDigital Library
- R. Fattal, M. Agrawala, and S. Rusinkiewicz. 2007. Multiscale shape and detail enhancement from multi-light image collections. ACM Trans. Graph. 26, 3. Google ScholarDigital Library
- R. Fattal, D. Lischinski, and M. Werman. 2002. Gradient domain high dynamic range compression. ACM Trans. Graph. 21, 3. Google ScholarDigital Library
- E. S. L. Gastal and M. M. Oliveira. 2011. Domain transform for edge-aware image and video processing. ACM Trans. Graph. 30, 3. Google ScholarDigital Library
- E. S. L. Gastal and M. M. Oliveira. 2012. Adaptive manifolds for real-time high-dimensional filtering. ACM Trans. Graph. 31, 4. Google ScholarDigital Library
- K. He, J. Sun, and X. Tang. 2010. Guided image filtering. In Proceedings of the European Conference on Computer Vision. Google ScholarDigital Library
- M. Kass. and J. Solomon. 2010. Smoothed local histogram filters. ACM Trans. Graph. 29, 3. Google ScholarDigital Library
- Y. Cli, L. Sharan, and E. H. Adelson. 2005. Compressing and companding high dynamic range images with subband architectures. ACM Trans. Graph. 24, 3, 836--844. Google ScholarDigital Library
- P. Mrzek, J. Weickert, and A. Bruhn. 2006. Robust estimation and smoothing with spatial and tonal kernels. In Geometric Properties from Incomplete Data. Springer.Google Scholar
- S. Paris and F. Durand. 2009. A fast approximation of the bilateral filter using a signal processing approach. Int. J. Comput. Vis. 81, 1, 24--52. Google ScholarDigital Library
- S. Paris, S. W. Hasinoff, and J. Kautz. 2011. Local laplacian filters: Edge-aware image processing with a laplacian pyramid. ACM Trans. Graph. 30, 4. Google ScholarDigital Library
- S. Paris, P. Kornprobst, J. Tumblin, and F. Durand. 2009. Bilateral filtering: Theory and applications. In Foundations and Trends in Computer Graphics and Vision. Google ScholarDigital Library
- P. Perona and J. Malik. 1990. Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12, 7, 629--639. Google ScholarDigital Library
- G. Petschnigg, M. Agrawala, H. Hoppe, R. Szeliski, M. Cohen, and K. Toyama. 2004. Digital photography with flash and no-flash image pairs. ACM Trans. Graph. 23, 3. Google ScholarDigital Library
- J. Ragan-Kelley, A. Adams, S. Paris, M. Levoy, S. Amarasinghe, and F. Durand. 2012. Decoupling algorithms from schedules for easy optimization of image processing pipelines. ACM Trans. Graph. 31, 3. Google ScholarDigital Library
- K. Subr, C. Soler, and F. Durand. 2009. Edge-preserving multi-scale image decomposition based on local extrema. ACM Trans. Graph. 28, 5. Google ScholarDigital Library
- K. Sunkavalli, M. K. Johnson, W. Matusik, and H. Pfister. 2010. Multi-scale image harmonization. ACM Trans. Graph. 29, 3. Google ScholarDigital Library
- C. Tomasi and R. Manduchi. 1998. Bilateral filtering for gray and color images. In Proceedings of the International Conference on Computer Vision. IEEE, 839--846. Google ScholarDigital Library
- M. Trenacoste, R. Mantiuk, W. Heidrich, and F. Dufroz. 2012. Unsharp masking, countershading and halos: Enhancements or artifacts? Comput. Graph. Forum 31, 2, 555--564. Google ScholarDigital Library
- J. Van De Weijer. and R. Van Den Boomgaard. 2002. On the equivalence of local-mode finding, robust estimation and mean-shift analysis as used in early vision tasks. In Proceedings of the International Conference on Pattern Recognition. Google ScholarDigital Library
- L. Xu, C. Lu, Y. Xu, and J. Jia. 2011. Image smoothing via l0 gradient minimization. ACM Trans. Graph. 30, 6. Google ScholarDigital Library
- J. Zhong and H. Sun. 2008. Wavelet-based multiscale diffusion with adaptive statistical analysis for image restoration. IEEE Trans. Circ. Syst. 55, 9.Google Scholar
Index Terms
- Fast Local Laplacian Filters: Theory and Applications
Recommendations
Local Laplacian filters: edge-aware image processing with a Laplacian pyramid
The Laplacian pyramid is ubiquitous for decomposing images into multiple scales and is widely used for image analysis. However, because it is constructed with spatially invariant Gaussian kernels, the Laplacian pyramid is widely believed as being unable ...
Adaptive fast local Laplacian filters and its edge-aware application
We present a new approach for edge-aware image processing, inspired by the principle of local Laplacian filters and fast local Laplacian filters. In contrast to the previous methods that primarily rely on fixed intensity threshold, our method adopts an ...
Performance Assessment of Edge Preserving Filters
Denoising is one of the important aspects in image processing applications. Denoising is the process of eliminating the noise from the noisy image. In most cases, noise accumulates at the edges. So that prevention of noise at edges is one of the most ...
Comments