A Multiscale Approach to Integrated Volume Segmentation and Rendering

Abstract

A number of techniques have been proposed for rendering volumetric scalar data sets. Techniques have also been proposed for analyzing the three dimensional information contents of the underlying domain, but traditionally the data analysis part is left as a post-processing step which only involves the rendered two dimensional images. In this paper, we describe a visualization method for scalar volume data which integrates explicit knowledge of the underlying domain into the rendering process. The key of this approach lies in a hierarchical description of the discrete signal, which is decomposed into a sequence of multiscale representations. We describe a technique for the analysis of structures within the data. This allows for the segmentation and classification of the relevant features and can be used to improve their visual sensation. We also address the problem of accelerating the final rendering pass by integrating the extracted object space information into the ray traversal process.