Dynaface is a computer application and Python library that measures facial symmetry. It utilizes advanced AI for both symmetric and asymmetric faces. AI allows Dynaface to locate 97 facial landmarks automatically to conduct a variety of measures on still images and videos. Researchers can export all data from pictures and videos to CSV/Excel format for further analysis.
The story behind Dynaface, from RGA
- Apple Store - MacOS/iPhone/iPad
- Microsoft Store - Windows 10/11
- Other versions: Download Latest Version or All Versions
- Users Guide
- Dynaface Library: Python Library, DotNet Library
Dynaface builds on three neural networks, all run via ONNX Runtime:
| # | Model | Role in Dynaface | File | License |
|---|---|---|---|---|
| 1 | BlazeFace (short-range) | Face bbox detection | blaze_face_short_range.onnx |
Apache-2.0 (MediaPipe) |
| 2 | SPIGA (WFLW-98) | 98-pt landmarks + head pose | spiga_wflw.onnx |
BSD-3-Clause |
| 3 | U²-Net | Background/saliency removal (lateral) | u2net.onnx |
Apache-2.0 |
You can download all three models from the current model bundle.
If you use Dynaface in academic work, please also cite their original authors:
- BlazeFace (face detection) — Bazarevsky, V., Kartynnik, Y., Vakunov, A., Raveendran, K., & Grundmann, M. (2019). BlazeFace: Sub-millisecond neural face detection on mobile GPUs. CVPR Workshop on Computer Vision for AR/VR. https://doi.org/10.48550/arXiv.1907.05047
- SPIGA (facial landmarks & head pose) — Prados-Torreblanca, A., Buenaposada, J. M., & Baumela, L. (2022). Shape preserving facial landmarks with graph attention networks. British Machine Vision Conference (BMVC). https://doi.org/10.48550/arXiv.2210.07233
- U²-Net (background removal) — Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O. R., & Jagersand, M. (2020). U²-Net: Going deeper with nested U-structure for salient object detection. Pattern Recognition, 106, 107404. https://doi.org/10.1016/j.patcog.2020.107404
- Renne, A., Heaton, J., & Boahene, K. D. O. (2026). Associations of AI-based facial metrics with patient-reported outcomes in idiopathic facial paralysis. Laryngoscope. Advance online publication. https://doi.org/10.1002/lary.70417
- BibTeX: https://github.com/jeffheaton/dynaface/blob/main/CITATION.bib
-
Renne, A., Heaton, J., Derakhshan, A., Nellis, J. C., Desai, S. C., & Boahene, K. D. (2025). Use of dynamic, automated facial analysis in quantifying oral-ocular synkinesis. Facial Plastic Surgery & Aesthetic Medicine. https://doi.org/10.1177/26893614251395737
-
Berges, A. J., Renne, A., Heaton, J., Leung, D. G., & Boahene, K. D. (2025). Facial weakness in facioscapulohumeral muscular dystrophy: Objective and patient-reported measures to guide reconstructive interventions. Facial Plastic Surgery & Aesthetic Medicine, Article 26893614251407675. https://doi.org/10.1177/26893614251407675
This application and Python library are licensed under the Apache License Version 2.0.