To counteract the sterile look of computer-generated worlds, we introduce a procedural model for worn edges that can be seen in buildings and stones: edges that have suffered minor damage at multiple points, resulting in material being chipped off. Employing data gathered from photographs, the method adds minute detail along exposed edges. The deformed geometry may be simulated with normal maps...

Adaptive network and exemplar-similarity models were compared on their ability to predict category learning and transfer data. An exemplar-based network (Kruschke, 1990a, 1990b, 1992) that combines key aspects of both modeling approaches was also tested. The exemplar-based network incorporates an exemplar-based category representation in which exemplars become associated to categories through t...

The idea that natural phenomena can be explained by means of exemplars or explanations of previous phenomena has often been proposed in the literature but never formally worked out. To the best of my knowledge, no exact mechanism exists that models new phenomena on previous ones, or that describes how problem solutions can be reused to explain new cases in science. In this paper, I attempt to d...

Realistic rendering of computer modeled three dimensional surfaces typically involves estimation of the reflectance properties of the material to be used for rendering the surface, or use of photographs of the material for texturing instead. Bidirectional texture functions (BTFs) can be used for this purpose, however, full coverage of all viewing and lighting directions desired must be acquired...

Exemplar-based learning or, equally, nearest neighbour methods have recently gained interest from researchers in a variety of computer science domains because of the prevalence of large amounts of accessible data and storage capacity. In computer vision, these types of technique have been successful in several problems such as scene recognition, shape matching, image parsing, character recognit...