Abstract
Many 3D objects in the world around us are strongly constrained. For instance, not only cultural artifacts but also many natural objects are bilaterally symmetric.
Human faces are an important case for which bilateral symmetry holds, at least approximatively. Can a priori information about generic constraints of this type
help the task of 3D object recognition? It can be shown that theoretically such prior information reduces the amount of information needed to recognize a 3D
object, since additional virtual views can be generated from given model views by the appropriate symmetry transformations. Under special conditions, a single
non-accidental ``model‘‘ view is theoretically sufficient for recognition of novel views, if the object is bilaterally symmetric, whereas the theoretical minimum
(under the same conditions) for a non-symmetric object is two views. In practice, we expect that the "virtual" views provided by the symmetry property will facilitate human recognition of novel views. Psychophysical experiments confirm that humans are better in the recognition of symmetric objects. The hypothesis of symmetry-induced virtual views together with a network model that successfully accounts for human recognition of generic 3D objects leads to predictions that we have verified with psychophysical experiments.
