Parameter Spaces of Cups - Cluster-based Exploration of a Geometry Generator’s Parameter Space (DAEV)

Geometry generators are commonly used in video games and evaluation systems for computer vision to create geometric shapes such as terrains, vegetation or airplanes. The parameters of the generator are often sampled automatically which can lead to many similar or unwanted objects. In this thesis, we propose a novel visual exploration approach that combines the abstract parameter space of the generator with the resulting geometric shapes in a composite visualization. Similar 3D shapes are first grouped using hierarchical clustering and then displayed in an illustrative parallel coordinates or scatterplot matrix visualization. This helps the user to study the sensitivity of the generator with respect to its parameter space and to identify invalid regions. Starting from a compact overview representation, the user can iteratively drill-down into local shape differences by clicking on the respective clusters. Additionally, a linked radial tree gives an overview of the cluster hierarchy and enables the user to manually split or merge clusters. We evaluate our approach by exploring the parameter space of a cup generator and provide feedback from domain experts.