Skip to content (access key 's')
Logo of Technion
Logo of CS Department
Events

The Taub Faculty of Computer Science Events and Talks

On Learning Geometric Differential Invariants
event speaker icon
Fatimah Alzahraa Fahoum (M.Sc. Thesis Seminar)
event date icon
Tuesday, 06.10.2026, 10:30
event location icon
Taub 401
event speaker icon
Advisor: Prof. Ron Kimmel

Classical approaches to geometric differential invariants begin by specifying a transformation group, analytically deriving the corresponding invariant differential quantities, and constructing numerical schemes to approximate them. This work takes a data-driven perspective and introduces a self-supervised deep learning framework for learning group-equivariant semi-local geometric operators directly from point samples of planar curves. Specifically, we train a neural network to act as a discrete differentiation operator. Remarkably, the learned operator behaves as a discrete approximation to differentiation with respect to the corresponding group-invariant arc length. The framework requires no fixed parameterization and remains robust under non-uniform sampling and noise. Experiments demonstrate that the learned operators generalize across a wide range of curve geometries and successfully handle line-preserving transformation groups, including the Euclidean, similarity and equi-affine groups. The learned differential operators transfer directly to downstream shape-analysis tasks without retraining. The resulting framework is a data-driven foundation for approximating geometric invariants from discrete observations.