Given a single view of an object, humans can readily recognize that object from other views that preserve the parts in the original view. Empirical evidence suggests that this capacity reflects the activation of a viewpoint-invariant structural description specifying the object's parts and the relations among them. This article presents a neural network that generates such a description. Structural description is made possible through a solution to the dynamic binding problem: Temporary conjunctions of attributes (parts and relations) are represented by synchronized oscillatory activity among independent units representing those attributes. Specifically, the model uses synchrony (a) to parse images into their constituent parts, (b) to bind together the attributes of a part, and (c) to bind the relations to the parts to which they apply. Because it conjoins independent units temporarily, dynamic binding allows tremendous economy of representation and permits the representation to reflect the attribute structure of the shapes represented.