Automatic Image Colorization Via Multimodal Predictions

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5304)


We aim to color greyscale images automatically, without any manual intervention. The color proposition could then be interactively corrected by user-provided color landmarks if necessary. Automatic colorization is nontrivial since there is usually no one-to-one correspondence between color and local texture. The contribution of our framework is that we deal directly with multimodality and estimate, for each pixel of the image to be colored, the probability distribution of all possible colors, instead of choosing the most probable color at the local level. We also predict the expected variation of color at each pixel, thus defining a non-uniform spatial coherency criterion. We then use graph cuts to maximize the probability of the whole colored image at the global level. We work in the L-a-b color space in order to approximate the human perception of distances between colors, and we use machine learning tools to extract as much information as possible from a dataset of colored examples. The resulting algorithm is fast, designed to be more robust to texture noise, and is above all able to deal with ambiguity, in contrary to previous approaches.


Color Space Support Vector Regression Color Variation Local Description Greyscale Image 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Levin, A., Lischinski, D., Weiss, Y.: Colorization using optimization. In: SIGGRAPH 2004, pp. 689–694. ACM Press, Los Angeles, California (2004)Google Scholar
  2. 2.
    Yatziv, L., Sapiro, G.: Fast image and video colorization using chrominance blending. IEEE Transactions on Image Processing 15(5), 1120–1129 (2006)CrossRefGoogle Scholar
  3. 3.
    Horiuchi, T.: Colorization algorithm using probabilistic relaxation. Image Vision Computing 22(3), 197–202 (2004)CrossRefGoogle Scholar
  4. 4.
    Takahama, T., Horiuchi, T., Kotera, H.: Improvement on colorization accuracy by partitioning algorithm in cielab color space. In: Aizawa, K., Nakamura, Y., Satoh, S. (eds.) PCM 2004. LNCS, vol. 3332, pp. 794–801. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  5. 5.
    Welsh, T., Ashikhmin, M., Mueller, K.: Transferring color to greyscale images. In: SIGGRAPH 2002: Proc. of the 29th annual conf. on Computer graphics and interactive techniques, pp. 277–280. ACM Press, New York (2002)CrossRefGoogle Scholar
  6. 6.
    Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., Salesin, D.H.: Image analogies. In: Fiume, E. (ed.) SIGGRAPH 2001, Computer Graphics Proceedings, pp. 327–340. ACM Press, New York (2001)Google Scholar
  7. 7.
    Irony, R., Cohen-Or, D., Lischinski, D.: Colorization by Example. In: Proceedings of Eurographics Symposium on Rendering 2005 (EGSR 2005), Konstanz, Germany, June 29–July 1, 2005, pp. 201–210 (2005)Google Scholar
  8. 8.
    Bay, H., Tuytelaars, T., Van Gool, L.: Surf: Speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954. Springer, Heidelberg (2006)Google Scholar
  9. 9.
    Schölkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge (2001)Google Scholar
  10. 10.
    Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. In: Figueiredo, M., Zerubia, J., Jain, A.K. (eds.) EMMCVPR 2001. LNCS, vol. 2134, pp. 359–374. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  11. 11.
    Kolmogorov, V., Zabih, R.: What Energy Functions Can Be Minimized via Graph Cuts? In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 65–81. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  12. 12.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. In: ICCV, pp. 377–384 (1999)Google Scholar
  13. 13.
    Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., Tappen, M.F., Rother, C.: A comparative study of energy minimization methods for markov random fields. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 16–29. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  14. 14.
    Blasi, G., Recupero, D.R.: Fast Colorization of Gray Images. In: Proc. of Eurographics Italian Chapter (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  1. 1.Pulsar Team, INRIASophia-AntipolisFrance
  2. 2.Wolfson Medical Vision Lab, Dpt. of Engineering ScienceUniversity of OxfordUK
  3. 3.Max Planck Institute for Biological CyberneticsTübingenGermany

Personalised recommendations