Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yazdi, Ali Shadman, Cappella, Annalisa, Baldini, Benedetta, Solazzo, Riccardo, Tartaglia, Gianluca, Sforza, Chiarella, Baselli, Giuseppe
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.00910
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917258420289536
author Yazdi, Ali Shadman
Cappella, Annalisa
Baldini, Benedetta
Solazzo, Riccardo
Tartaglia, Gianluca
Sforza, Chiarella
Baselli, Giuseppe
author_facet Yazdi, Ali Shadman
Cappella, Annalisa
Baldini, Benedetta
Solazzo, Riccardo
Tartaglia, Gianluca
Sforza, Chiarella
Baselli, Giuseppe
contents 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 stereo-photogrammetry facial models. The method combines coarse alignment, region-of-interest filtering, and an initial approximation of landmarks 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 preserves relevant anatomical distances with a 2.822 mm average error, comparable to intra-observer variability. To assess generalization, the model was further evaluated on 700 subjects from the FaceScape dataset, achieving a point-wise error of 0.41\,mm and a distance-wise error of 0.38\,mm. Compared to 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 found at https://github.com/Ali5hadman/PAL-Net-A-Point-Wise-CNN-with-Patch-Attention
format Preprint
id arxiv_https___arxiv_org_abs_2510_00910
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PAL-Net: A Point-Wise CNN with Patch-Attention for 3D Facial Landmark Localization
Yazdi, Ali Shadman
Cappella, Annalisa
Baldini, Benedetta
Solazzo, Riccardo
Tartaglia, Gianluca
Sforza, Chiarella
Baselli, Giuseppe
Computer Vision and Pattern Recognition
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 stereo-photogrammetry facial models. The method combines coarse alignment, region-of-interest filtering, and an initial approximation of landmarks 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 preserves relevant anatomical distances with a 2.822 mm average error, comparable to intra-observer variability. To assess generalization, the model was further evaluated on 700 subjects from the FaceScape dataset, achieving a point-wise error of 0.41\,mm and a distance-wise error of 0.38\,mm. Compared to 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 found at https://github.com/Ali5hadman/PAL-Net-A-Point-Wise-CNN-with-Patch-Attention
title PAL-Net: A Point-Wise CNN with Patch-Attention for 3D Facial Landmark Localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.00910