An Occlusion Model Generating Scale-Invariant Images

Ann B. Lee and David Mumford

We present a model for scale invariance of natural images based on the ideas of images as collages of statistically independent objects. The model takes occlusions into account, and produces images that show translational invariance, and approximate scale invariance under block averaging and median filtering. We compare the statistics of the simulated images with data from natural scenes, and find good agreement for short-range and middle-range statistics. Furthermore, we discuss the implications of the model on a 3D description of the world.

gzipped postscript file