Augmented Equivariant Mesh Networks for Anatomical Segmentation

Excerpt

arXiv:2605.08172v2 Announce Type: replace-cross Abstract: Anatomical mesh segmentation requires models that operate directly on irregular surface geometry while remaining robust to changes in coordinate pose across meshes of varying resolution. Existing task-specific mesh and point-cloud methods are not equivariant, and can degrade sharply under test-time perturbation, for example dropping by 28-30 IoU points on 3D-IOSSeg at $40^\circ$ rotation even with matched training augmentation. We present