PAL-Net: A point-wise CNN with patch-attention for 3D anatomical facial landmark localization

Manual annotation of anatomical landmarks on 3D facial scans is a time-consuming and expertise-dependent task, yet it remains critical for clinical assessments, morphometric analysis, and craniofacial research. While several deep learning methods have been proposed for facial landmark localization, most focus on pseudo-landmarks or require complex input representations, limiting their clinical applicability. This study presents a fully automated deep learning pipeline (PAL-Net) for localizing 50 anatomical landmarks on facial models acquired via stereo-photogrammetry. The method combines coarse alignment, region-of-interest filtering, and an initial landmark approximation with a patch-based pointwise CNN enhanced by attention mechanisms. Trained and evaluated on 214 annotated scans from healthy adults, PAL-Net achieved a mean localization error of 3.686 mm and preserved relevant anatomical distances with an average error of 2.822 mm. While the geometric error exceeds expert intra-observer variability, the distance-wise error maintains structural integrity sufficient for high-throughput anthropometric analysis. To assess generalization, the model was further evaluated on 700 subjects from the FaceScape dataset, achieving a mean localization error of 0.41 mm and a distance error of 0.38 mm. Comparing with existing methods, PAL-Net offers a favorable trade-off between accuracy and computational cost. While performance degrades in regions with poor mesh quality (e.g., ears, hairline), the method demonstrates consistent accuracy across most anatomical regions. PAL-Net generalizes effectively across datasets and facial regions, outperforming existing methods in both point-wise and structural evaluations. It provides a lightweight, scalable solution for high-throughput 3D anthropometric analysis, with potential to support clinical workflows and reduce reliance on manual annotation. Source code can be accessed at https://github.com/Ali5hadman/PAL-Net-A-Point-Wise-CNN-with-Patch-Attention