Advertisement

Intrinsic Image Decomposition with Local Smooth Assumption and Global Color Assumption

  • Zhongqiang Wang
  • Li Zhu
Conference paper
  • 1.7k Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7633)

Abstract

Intrinsic images, which describe independent characteristics of scenes, are very useful in many different fields. But it is difficult to get them because the problem is extremely ill-posed. Smooth assumption is widely used in many methods, but pixels in plain areas and in edge areas are not well distinguished. We improve this assumption by adding a weight to every pixel in the image so that the smoothness is measured accordingly. There are always large error in dark areas in previous methods due to the enlarged inaccuracy there. We proposed a global assumption to solve this problem. The results show that the performance is greatly improved by using our method.

Keywords

intrinsic image smooth assumption color line assumption 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barrow, H., Tenenbaum, J.: Recovering intrinsic scene characteristics from images. Computer Vision Systems 1Google Scholar
  2. 2.
    Bousseau, A., Paris, S., Durand, F.: User-assisted intrinsic images. ACM Trans. Graph. 28(5), 130:1–130:10 (2009) 1, 2CrossRefGoogle Scholar
  3. 3.
    Carroll, R., Ramamoorthi, R., Agrawala, M.: Illumination decomposition for material recoloring with consistent interreflections. In: SIGGRAPH 2011 (August 2011) 1Google Scholar
  4. 4.
    Omer, I., Werman, M.: Color lines: Image specific color representation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2004) 1, 2, 4, 7Google Scholar
  5. 5.
    Weiss, Y.: Deriving intrinsic images from image sequences. In: ICCV, pp. 68–75 (2001) 2Google Scholar
  6. 6.
    Matsushita, Y., Lin, S., Kang, S.B., Shum, H.-Y.: Estimating Intrinsic Images from Image Sequences with Biased Illumination. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004, Part II. LNCS, vol. 3022, pp. 274–286. Springer, Heidelberg (2004) 2CrossRefGoogle Scholar
  7. 7.
    Liu, X., Wan, L., Qu, Y., Wong, T.-T., Lin, S., Leung, C.-S., Heng, P.-A.: Intrinsic colorization. ACM Transactions on Graphics (SIGGRAPH Asia 2008 Issue) 27(5), 152:1–152:9 (2008) 2zbMATHCrossRefGoogle Scholar
  8. 8.
    Bell, M., Freeman, W.T., Bell, M., Freeman, W.T.: Learning local evidence for shading and reflection. In: Proceedings of the IEEE International Conference on Computer Vision (2001) 2Google Scholar
  9. 9.
    Kimmel, R., Elad, M., Shaked, D., Keshet, R., Sobel, I.: A variational framework for retinex. International Journal of Computer Vision (2003) 2, 3Google Scholar
  10. 10.
    Shen, L., Yeo, C.: Intrinsic images decomposition using a local and global sparse representation of reflectance. In: CVPR, pp. 697–704. IEEE (2011) 2, 6, 7Google Scholar
  11. 11.
    Gehler, P.V., Rother, C., Kiefel, M., Zhang, L., Scholkopf, B.: Recovering intrinsic images with a global sparsity prior on reflectance. In: NIPS, pp. 765–773 (2011) 2, 3Google Scholar
  12. 12.
    Shen, L., Tan, P., Lin, S.: Intrinsic image decomposition with non-local texture cues. In: CVPR. IEEE Computer Society (2008) 2Google Scholar
  13. 13.
    Shen, J., Yang, X., Jia, Y., Li, X.: Intrinsic images using optimization. In: CVPR, pp. 3481–3487. IEEE (2011) 2Google Scholar
  14. 14.
    Sinha, P., Adelson, E.: Recovering reflectance and illumination in a world of painted polyhedra. In: Proc. 4th Int. Conf. on Comp. Vis., pp. 156–163 (1993) 2Google Scholar
  15. 15.
    Grosse, R., Johnson, M.K., Adelson, E.H., Freeman, W.T.: Ground-truth dataset and baseline evaluations for intrinsic image algorithms. In: International Conference on Computer Vision, pp. 2335–2342 (2009) 2, 3, 5Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Zhongqiang Wang
    • 1
  • Li Zhu
    • 1
  1. 1.Xi’an Jiaotong UniversityChina

Personalised recommendations