An Object Space Approach for Outermost Silhouettes Extraction

Abstract

Conspicuous outermost silhouette edges reveal the peculiar portrayal of model, and it is useful for applications, such as motion blur, morphing, simplification, skeletonization, etc. We propose a practical and effective approach to approximately extract the outermost silhouette edges from polygonal models under arbitrarily perspective views. All facet-normals and edges are encapsulated into a hierarchical tree in the preprocessing phase to facilitate the extraction of outermost silhouette edges. A two-stage extraction procedure is used at run-time. The first stage prunes edges, hardly to be recognized as the outermost silhouette edges using the inclusion relationship. The remaining edges are then used to approximate the outermost silhouette edges with respect to the intersection tests in the second stage. Experimental results show that our approach is effective and sufficient to most applications.