Testing Probabilistic Models of Binocular 3d Motion Perception

Geometric constraints for the perception of three-dimensional (3D) binocular motion are discussed in a probabilistic framework. Two alternative Bayesian models of binocular integration are put forward to explain perceptual bias under uncertainty. The models exploit biologically plausible constraints of local motion and disparity processing in a binocular viewing geometry. Results from computer simulations and model selection support the idea that disparity processing rather than motion processing introduces perceptual bias in 3D motion. This suggests that the binocular motion system combines motion and disparity constraints relatively late when establishing a 3D motion percept.