Geometry compression

This paper introduces the concept of Geometry Compression, allowing 3D triangle data to be represented with a factor of 6 to 10 times fewer bits than conventional techniques, with only slight losses in object quality. The technique is amenable to rapid decompression in both software and hardware implementations; if 3D rendering hardware contains a geometry decompression unit, application geometry can be stored in memory in compressed format. Geometry is first represented as a generalized triangle mesh, a data structure that allows each instance of a vertex in a linear stream to specify an average of two triangles. Then a variable length compression is applied to individual positions, colors, and normals. Delta compression followed by a modified Huffman compression is used for positions and colors; a novel table-based approach is used for normals. The table allows any useful normal to be represented by an 18-bit index, many normals can be represented with index deltas of 8 bits or less. Geometry compression is a general space-time tradeoff, and offers advantages at every level of the memory/interconnect hierarchy: less storage space is needed on disk, less transmission time is needed on networks.