Multiresolution data modelling for irregular data fields based onwavelets

摘要

In many applications of scientific visualization, the data fieldsare so large that they are very expensive to store, transmit and render.Multiresolution offers a promising new approach for addressing thesedifficulties on a simple, unified way. Wavelets provide an extremelyuseful mathematical toolkit for hierarchically decomposing functions inways that are both efficient and theoretically sound. This paper focuseson extension of wavelet based multiresolution to arbitrary topologicaldata grid. Using wavelet transform, the method proposed here obtains aunique shape description of an irregular data field. A biorthogonalvolume wavelet is constructed. Recursive subdivision is applied toirregular data field and leads to a collection of refinable scalingfunctions and hence to a sequence of nested linear spaces, as requiredby multiresolution. In order to overcome the subdivision connectivityrestriction, an applicable method is presented to convert the completelyarbitrary data field to multiresolution so that the technique forcreating multiresolution can be used