Abstract

Abstract. Binocular information about the structure of a scene is contained in the relative positions of corresponding points in the two views. If the eyes rotate, in order to fixate a different target, then the disparity at a given image location is likely to change. Quite different disparities can be produced at the same location, as the eyes move from one fixation-point to the next. The pointwise variability of the disparity map is problematic for biological visual systems, in which stereopsis is based on simple, short-range mechanisms. It is argued here that the problem can be addressed in two ways; firstly by an appropriate representation of disparity, and secondly by learning the typical pattern of image correspondences. It is shown that the average spatial structure of the disparity field can be estimated, by integrating over a series of binocular fixations. An algorithm based on this idea is tested on natural images. Finally, it is shown how the average pattern of disparities could help to put the images into binocular correspondence. 1

Citations