Graph Neural Networks for 3D facial morphology: Assessing the effectiveness of anthropometric and automated landmark detection

Giuseppe Maurizio Facchi, Giuliano Grossi, Alessandro D’Amelio, Francesco Agnelli, Chiarella Sforza, Gianluca Martino Tartaglia, Raffaella Lanzarotti

Abstract: Highlights•Learning 3D facial features to classify gender and age.•Comparing anthropometric vs. automatic landmarks and FPS sub-sampling.•Characterizing graph nodes with local and global geometric features.•Comparing GCN, GAT, DynamicEdgeConv, and Transformer models.

External IDs:doi:10.1016/j.patrec.2025.04.028