The Visual Computer

, Volume 26, Issue 6–8, pp 943–950 | Cite as

A GPU-based matting Laplacian solver for high resolution image matting

  • Mengcheng Huang
  • Fang Liu
  • Enhua Wu
Original Article


The recently proposed matting Laplacian (Levin et al., IEEE Trans. Pattern Anal. Mach. Intell. 30(2):228–242, 2008) has been proven to be a state-of-the-art method for solving the image matting problem. Using this method, matting is formulated as solving a high-order linear system which is hard-constrained by the input trimap. The main drawback of this method, however, is the high computational cost. As the size of the input image increases, the matting Laplacian becomes expensive to solve in terms of both memory and computational time.

In this paper we propose a GPU-based matting Laplacian solution which is dramatically faster than a conventional CPU solution, and at the same time largely reduces the memory consumption, making this method practical for the first time for high resolution image matting. To achieve this end, we employ a novel hierarchical windowing scheme to approximate the global optimal solution by solving a serial of local regions at multiple scales. We further employ a GPU-based local solver which can efficiently evaluate local solutions under various boundary conditions. Experimental results show that our system in general is more than two orders of magnitude faster than traditional CPU-based solvers, with about 80% less memory footprint.


Image matting Matting Laplacian Conjugate gradient solver GPU 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agarwala, A.: Efficient gradient-domain compositing using quadtrees. ACM Trans. Graph. 26(3), 94–98 (2007) CrossRefGoogle Scholar
  2. 2.
    Harris, M.: Optimizing parallel reduction in CUDA. Tech. Rep., NVIDIA Corporation (2007) Google Scholar
  3. 3.
    Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 228–242 (2008) CrossRefGoogle Scholar
  4. 4.
    NVIDIA: NVIDIA CUDA: Compute unified device architecture. NVIDIA Corporation (2008) Google Scholar
  5. 5.
    Rhemann, C., Rother, C., Wang, J., Gelautz, M., Kohli, P., Rott, P.: A perceptually motivated online benchmark for image matting. In: Proc. of IEEE CVPR, pp. 1826–1833 (2009) Google Scholar
  6. 6.
    Saad, Y.: Iterative Methods for Sparse Linear Systems, 2nd edn. Society for Industrial and Applied Mathematics, Philadelphia (2003) zbMATHGoogle Scholar
  7. 7.
    Szeliski, R.: Locally adapted hierarchical basis preconditioning. ACM Trans. Graph. 25(3), 1135–1143 (2006) CrossRefGoogle Scholar
  8. 8.
    Wang, J., Agrawala, M., Cohen, M.: Soft scissors: An interactive tool for realtime high quality matting. In: Proc. of ACM SIGGRAPH, pp. 9–14 (2007) Google Scholar
  9. 9.
    Wang, J., Cohen, M.: Optimized color sampling for robust matting. In: Proc. of IEEE CVPR, pp. 1–8 Google Scholar
  10. 10.
    Wang, J., Cohen, M.: Image and video matting: A survey. Found. Trends Comput. Graph. Vis. 3(2), 97–175 (2007) CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  1. 1.State Key Lab of Computer Science, Institute of SoftwareChinese Academy of SciencesBeijingChina
  2. 2.Graduate University of Chinese Academy of SciencesBeijingChina
  3. 3.Department of Computer and Information Science, Faculty of Science and TechnologyUniversity of MacauMacaoChina

Personalised recommendations