Perceptual organization and the representation of natural form
Artificial Intelligence
From volumes to views: an approach to 3-D object recognition
CVGIP: Image Understanding - Special issue on directions in CAD-based vision
Recognition of planar shapes from perspective images using contour-based invariants
CVGIP: Image Understanding
Object recognition through invariant indexing
Object recognition through invariant indexing
Binocular shape reconstruction: psychological plausibility of the 8-point algorithm
Computer Vision and Image Understanding
Towards an Affordance-Based Theory of Collaborative Action CoAct
International Journal of e-Collaboration
Hi-index | 0.00 |
This paper reviews main approaches to 3D shape perception in both human and computer vision. The approaches are evaluated with respect to their plausibility of generating adequate explanations of human vision. The criterion for plausibility is provided by existing psychophysical results. A new theory of 3D shape perception is then outlined. According to this theory, human perception of shapes critically depends on a priori shape constraints: symmetry and compactness. The role of depth cues is secondary, at best.