3-D SHAPE RECOVERY USING DISTRIBUTED ASPECT MATCHING

We present an approach to the recovery of 3-D volumetric primitives from a single 2-D image. The approach first takes a set of 3-D volumetric modeling primitives and generates a hierarchical aspect representation based on the projected surfaces of the primitives; conditional probabilities capture the ambiguity of mappings between levels of the hierarchy [15]. From a region segmentation of the input image, we present a novel formulation of the recovery problem based on the grouping of the regions into aspects. No domain-dependent heuristics are used; we exploit only the probabilities inherent in the aspect hierarchy. Once the aspects are recovered, we use the aspect hierarchy to infer a set of volumetric primitives and their connectivity. As a front end to an object recognition system, the approach provides the indexing power of complex 3-D object-centered primitives while exploiting the convenience of 2-D viewer-centered aspect matching. However, unlike traditional aspect matching paradigms that represent the entire object with a set of aspects, we use aspects to represent a finite vocabulary of 3-D parts from which objects can be constructed. Thus, the size of our aspect set is fixed and, more important, independent of the size of the object database. The method not only fully accommodates occlusion but uses the aspect hierarchy to overcome image segmentation errors. We describe the approach in detail and demonstrate its application to both synthetic line drawings and real images.