Splatting multiresolution volume data using the feature graph

We propose to represent classified datasets as a feature graph storing different graphical models and attributes for each feature. This graph allows us to render each feature according to its own characteristics. In addition, we show that various features of the graph storing volume information at different resolution levels can be rendered together using a view-aligned splatting method. Moreover, we propose a 2D kernel function for splats that is easy to tune and generates smaller footprints that reduce the render time. Our algorithm provides images with less blur. It enhances the boundary of the features while avoiding the subdivision of homogeneous regions of the volume