Covariant Derivatives and Vision

  • Todor Georgiev
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3954)


We describe a new theoretical approach to Image Processing and Vision. Expressed in mathemetical terminology, in our formalism image space is a fibre bundle, and the image itself is the graph of a section on it. This mathematical model has advantages to the conventional view of the image as a function on the plane: Based on the new method we are able to do image processing of the image as viewed by the human visual system, which includes adaptation and perceptual correctness of the results. Our formalism is invariant to relighting and handles seamlessly illumination change. It also explains simultaneous contrast visual illusions, which are intrinsically related to the new covariant approach.

Examples include Poisson image editing, Inpainting, gradient domain HDR compression, and others.


Covariant Derivative Human Visual System Image Space Texture Image Grayscale 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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Adobe Systems: Photoshop 7.0 User Guide. Adobe Systems, San Jose (2002)Google Scholar
  2. 2.
    Bertalmio, M., Sapiro, G., Castelles, V., Ballester, C.: Image Inpainting. In: Proceedings of ACM SIGGRAPH 2000, pp. 417–424. ACM Press, New York (2000)Google Scholar
  3. 3.
    Choquet-Bruhat, Y., DeWitt-Morette, C.: Analysis, Manifolds and Physics. North-Holland, Amsterdam (1982)MATHGoogle Scholar
  4. 4.
    Choudhury, P., Tumblin, J.: The Trilateral Filter for High Contrast Images and Meshes. In: Proceedings of the 2003 Eurographics Symposium on Rendering, pp. 186–196 (2003)Google Scholar
  5. 5.
    Fattal, R., Lischinski, D., Werman, M.: Gradient Domain High Dynamic Range Compression. In: Proceedings of ACM SIGGRAPH 2002, pp. 249–256 (2002)Google Scholar
  6. 6.
    Horn, B.: Determining Lightness from an Image. Computer Graphics and Image Processing 3, 277–299 (1974)CrossRefGoogle Scholar
  7. 7.
    Koenderink, J.J., van Doorn, A.J.: Image Processing Done Right. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 158–172. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  8. 8.
    Land, E., McCann, J.: Lightness and Retinex Theory. Journal of the Optical Society of America 61(1), 1–11 (1971)CrossRefGoogle Scholar
  9. 9.
    Mangiarotti, L., Sardanashvily, G.: Gauge Mechanics. World Scientific, North-Holland (1998)CrossRefMATHGoogle Scholar
  10. 10.
    Pérez, P., Gangnet, M., Blake, A.: Poisson Image Editing. In: Proceedings of ACM SIGGRAPH 2003, pp. 313–318 (2003)Google Scholar
  11. 11.
    Press, W., Teukolsky, S., Vetterling, W., Flannery, B.: Numerical Recipes in C. Cambridge University Press, Cambridge (1992)MATHGoogle Scholar
  12. 12.
    Saunders, D.: The Geometry of Jet Bundles. Cambridge University Press, Cambridge (1989)CrossRefMATHGoogle Scholar
  13. 13.
    Tomasi, C., Manduchi, R.: Bilateral Filtering for Gray and Color Images. In: Proceedings IEEE Int. Conf. on Computer Vision, pp. 836–846 (1998)Google Scholar
  14. 14.
    Gazzaniga, M.: The New Cognitive Neurosciences, pp. 339–351. MIT Press, Cambridge (2000)Google Scholar
  15. 15.
    Seckel, A.: The Art of Optical Illusions. Carlton Books (2000)Google Scholar
  16. 16.
    Raskar, R., Ilie, A., Yu, J.: Image Fusion for Enhancing Context in Images and Video. In: ACM Nonphotorealistic Animation and Rendering, NPAR (2004)Google Scholar
  17. 17.
    Bertalmio, M., Vese, L., Sapiro, G., Osher, S.: Simultaneous Structure and Texture Image Inpainting. In: CVPR, vol. (2), pp. 707–712 (2003)Google Scholar
  18. 18.
    Petitot, J.: The neurogeometry of pinwheels as a sub-Riemannian contact structure. Journal of Physiology - Paris 97, 265–309 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Todor Georgiev
    • 1
  1. 1.Adobe SystemsSan JoseUSA

Personalised recommendations