This research group develops concepts and practical solutions for the analysis and processing of geometric data such as shapes, graphs, and abstract data sets alike. We account for the rich structure therein via intrinsic approaches that ensure consistency and reduce bias, thereby providing improved analytical power. To this end, the group builds upon and aims at extending the theory, algorithms, and applications of non-Euclidean statistics, geometric deep learning, and applied geometry.

Current applications revolve around shape analysis in the context of medicine, archaeology, and fashion. A particular focus lies on the study of data together with co-varying parameters like time. Examples include among others regression of disease-specific shape variations, morphological classification, and identification of systematic differences at population-level.

Morphomatics The algortihms developed within the group are released as parts of the open source Morphomatics library. It contains Python-based implementations of the intrinsic manifold-based methods and is freely available on GitHub.