Abstract
This paper presents a GPU-based implementation for constructing edge-preserving multiscale image decompositions. An input image is decomposed into a piecewise smooth base layer and multiple detail layers. The base layer captures large scale variations in the image, while the detail layers contain the small scale details. The detail layers are progressively obtained with the edge-preserving weighted least squares optimizations. The improvement of performance is achieved by introducing a Jacobi-like GPU solver, which converges to the right solution much faster than the standard Jacobi iterator. Note that the whole pipeline design is highly parallel, enabling a real-time implementation. Several experimental examples on edge-preserving tonal adjustment and image abstraction are shown to demonstrate the feasibility of the proposed method.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Buatois, L., Caumon, G., Lévy, B.: Concurrent number cruncher: An efficient sparse linear solver on the GPU. In: Perrott, R., Chapman, B.M., Subhlok, J., de Mello, R.F., Yang, L.T. (eds.) HPCC 2007. LNCS, vol. 4782, pp. 358–371. Springer, Heidelberg (2007)
Chen, J., Paris, S., Durand, F.: Real-Time Edge-Aware Image Processing with the Bilateral Grid. ACM Transactions on Graphics, 26(3), Article 103 (2007)
Farbman, Z., Fattal, R., Lischinski, D., Szeliski, R.: Edge-Preserving Decompositions for Multi-scale Tone and Detail Manipulation. Proc. of ACM SIGGRAPH ’08, ACM, article 67 (2008)
Fattal, R., Agrawala, M., Rusinkiewicz, S.: Multiscale Shape and Detail Enhancement from Multi-light Image Collections, Proc. of ACM SIGGRAPH ’07, ACM, article 51 (2007)
Goodnight, N., Woolley, C., Lewn, G., Luebke, D., Humphreys, G.: A Multigrid Solver for Boundary Value Problems using Programmable Graphics Hardware. In: Proc. of EUROGRAPHICS/SIGGRAPH Workshop on Graphics Hardware 2003, pp. 102–111. EUROGRAPHICS Association (2003)
Lischinski, D., Farbman, Z., Uytendaele, M., Szeliski, R.: Interactive Local Adjustment of Tonal Values. ACM Transactions on Graphics 25(3), 646–653 (2006)
Ian, J.B., Farmer, I., Grinspun, E., Schroeder, P.: Sparse Matrix Solvers on the GPU: Conjugate Gradients and Multigrid. In: Proc. of ACM SIGGRAPH 2003, pp. 917–924. ACM, New York (2003)
Jeschke, S., Cline, D., Wonka, P.: A GPU Laplacian Solver for Diffusion Curves and Poisson Image Editing. In: Proc. of ACM SIGGRAPH Asia 2009, pp. 1–8. ACM, New York (2009)
NVIDIA Corp.: CUDA Programming Guid for CUDA Toolkit 3.0 (2010), http://developer.nvidia.com/object/gpucomputing.html
Perona, P., Malik, J.: Scale-Space and Edge Detection using Anisotropic Diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(7), 629–639 (1990)
Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipies in C: the Art of Scientific Computing, pp. 871–888. Cambridge University Press, New York (1992)
Tomasi, C., Manduchi, R.: Bilateral Filtering for Gray and Color Images. In: Proc. of IEEE International Conference on Computer Vision (ICCV 1998), pp. 839–846 (1998)
Tumblin, J., Turk, G.: LCIS: A Boundary Hierarchy for Detail-Preserving Contrast Reduction. In: Proc. ACM SIGGRAPH 1999, pp. 83–90. ACM, New York (1999)
Winnemöller, H., Olsen, S., Gooch, B.: Real-Time Video Abstraction. ACM Transactions on Graphics 25(3), 1221–1226 (2006)
Wyszecki, G., Stiles, W.: Color Science: Concepts and Methods, Quantitative Data and Formulae. Wiley, New York (1982)
Zhao, H., Jin, X., Shen, J., Mao, X., Feng, J.: Real-time Feature-Aware Video Abstraction. The Visual Computer 24(7-9), 727–734 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Li, Q., Zhao, H. (2011). Real-Time Implementation for Weighted-Least-Squares-Based Edge-Preserving Decomposition and Its Applications. In: Pan, Z., Cheok, A.D., Müller, W. (eds) Transactions on Edutainment VI. Lecture Notes in Computer Science, vol 6758. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22639-7_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-22639-7_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22638-0
Online ISBN: 978-3-642-22639-7
eBook Packages: Computer ScienceComputer Science (R0)