The Generic Viewpoint Assumption in a Bayesian Framework
|MERL Report: ||TR93-11a: William T. Freeman
Bayesian Perspectives on Perception, David Knill and Whitman Richards, editors, Cambridge University Press, 1996
The "generic view" assumption states that an observer is not in a special position relative to the scene. It is commonly used to disqualify scene interpretations that assume special viewpoints, following a binary decision that the viewpoint was either generic or accidental. In this chapter, we show how to use the generic view assumption to quantify the likelihood of a view. This quantitative approach can be applied to estimate scene parameters. This approach applies to many vision problems. We show shape from shading examples where we rank shapes or reflectance functions in cases which are otherwise ambiguous. The rankings agree with the perceived values.