A computational model for understanding three-dimensional view space

This paper presents a computational model for understanding three-dimensional (3D) view space. In the approach, object faces are used as perceptual entities in accordance with the visual perception on shape constancy and face-pose consistency. To accommodate the perceptual knowledge of face visibilities of objects, a perceptual model of view space is developed from which the shape constancy can be perceived and face-pose consistency can be estimated qualitatively