“Unbiased sampling techniques for image synthesis” by Kirk and Arvo

  • ©David Kirk and James (Jim) Arvo




    Unbiased sampling techniques for image synthesis



    We examine a class of adaptive sampling techniques employed in image synthesis and show that those commonly used for efficient anti-aliasing are statistically biased. This bias is dependent upon the image function being sampled as well as the strategy for determining the number of samples to use. It is most prominent in areas of high contrast and is attributable to early stages of sampling systematically favoring one extreme or the other. If the expected outcome of the entire adaptive sampling algorithm is considered, we find that the bias of the early decisions is still present in the final estimator. We propose an alternative strategy for performing adaptive sampling that is unbiased but potentially more costly. We conclude that it may not always be practical to mitigate this source of bias, but as a source of error it should be considered when high accuracy and image fidelity are a central concern.


    1. Arvo, james, and David Kirk, “Particle Transport and Image Synthesis,” Computer graphics, 24(4) August 1990,pp, 63-66.
    2. Dippe, Mark A. Z., and Erling Henry Wold, “An tialiasing through stochastic sampling,” Computer Graphics, 19(3), July 1985, pp.69-78.
    3. Freund, Jhon Ei., and Ronald E.Walpole, Mathematical Statistics, 4th edition, Prentice Hall, New Jersey, 1987.
    4. Glassner, Andrew S., “An oevrview of Ray Tracing,” in An Introduction to Ray Tracing, A, S, Glassner, ed,, Academic Press, New York, 1989.
    5. Kajiya,J. T:,,The Rendering Eqiuation,” Computer Graphics, 20(4), August 1986,pp.143-150.
    6. Lee, Mark. E. Richard A.Redner, and Samuel P. Uselton, “Statistically Optimized Sampling for Distributed Ray Tracing,” Computer Graphics, 19(3), July 1985,pp.61-68.
    7. Mitchell,. Don P., “Generating Antialiased Images at Low Sampling Densities,” computer Graphics, 21(4) July 1987,pp,65-69.
    8. Painter, James,and Kenneth Sloan, “Antialiased Ray Tracing by Adaptive Progressive Refinement,” Computer Graphics, 23(3), July 1989, pp,281-288.
    9. Purgathofer, W, “A Statistical Method for Adaptive Stcthostic sampling,” in Proceedings of Eurographics 86, ed.A.A.G. Reauicha, Elsevier, North-Holland, 1986,pp.145-152.
    10. Rubinstein, R.Y., Simulation and the Monte Carlo Method, J.Wiley, New york, 1981.
    11. Whitted,turner, “An Improved Illumination model for Shaded Display, ” Communication of the ACM, 32(6), June 1980, pp.343-349.

ACM Digital Library Publication: