The asp: A continuous viewer-centered representation for 3D object recognition

In the paper the authors present a new representation for polyhedral objects which is a continuous generalization of multiview representations. That is, they show how to represent views or images of an object (i.e., the appearance of the object) continuously over all viewpoints. The authors then show how this representation overcomes some of the drawbacks of multiview representation for object recognition, namely, that the image to be recognized will usually not match one of the stored images exactly, that the representation contains no information about how to interpolate between views, and that the representation is large.