Efficient Compression of Non-Manifold Polygonal Meshes

We present a method for compressing non-manifold polygonalmeshes, i.e. polygonal meshes with singularities, which occur veryfrequently in the real-world. Most efficient polygonal compressionmethods currently available are restricted to a manifold mesh: theyrequire a conversion process, and fail to retrieve the original modelconnectivity after decompression. The present method works byconverting the original model to a manifold model, encoding themanifold model using an existing mesh compression technique, andclustering, or stitching together during the decompression processvertices that were duplicated earlier to faithfully recover the originalconnectivity. This paper focuses on efficiently encoding and decodingthe stitching information. By separating connectivity fromgeometry and properties, the method avoids encoding vertices (andproperties bound to vertices) multiple times; thus a reduction of thesize of the bit-stream of about 10% is obtained compared with encodingthe model as a manifold.