Parallelised Differentiable Straightest Geodesics for 3D Meshes

ArXi:2603.15780v1 Announce Type: cross Machine learning has been progressively generalised to operate within non-Euclidean domains, but geometrically accurate methods for learning on surfaces are still falling behind. The lack of closed-form Riemannian operators, the non-differentiability of their discrete counterparts, and poor parallelisation capabilities have been the main obstacles to the development of the field on meshes.