Select muscles or load an example, then click Render
Rendering…
1. Pick an input mode, or click an example pill (smile, surprise…).
2. Active muscles — drag a slider to set each muscle's activation (0–1). Choose side: both / L / R / L+R (two independent sliders per muscle). Tick absolute for raw µV values (set a max).
3. Click Render. The image appears on the right with a download button.
4. Advanced tab adds modes (Expression, FACS, Grid, sEMG, Custom JSON) + Camera & View.
Tip: drag the divider beside the sidebar to widen it (handy in L+R mode).
Select muscles or load an example, then click Render
Rendering…
MyoVision renders a 3D head muscle model with per-muscle activation highlighting, for visualizing which facial muscles are active — e.g. for emotion/expression analysis, sEMG, or FACS pipelines.
Input modes
Renders run server-side; the licensed 3D model never leaves the host. Default output is JPEG (small payloads); request format: "png" for lossless.
How to cite
If you use this tool in your work, please cite it:
@inproceedings{buechner2025electromyography,
doi = {10.1109/CVPR52734.2025.00029},
year = {2025},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
title = {Electromyography-Informed Facial Expression Reconstruction for Physiological-Based Synthesis and Analysis},
author = {Tim Büchner and Christoph Anders and Orlando Guntinas-Lichius and Joachim Denzler},
}
Büchner, T., Anders, C., Guntinas-Lichius, O., & Denzler, J. (2025). Electromyography-Informed Facial Expression Reconstruction for Physiological-Based Synthesis and Analysis. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR52734.2025.00029
Herausgeber / Provider
Lehrstuhl Digitale Bildverarbeitung
Computer Vision Group Jena
Friedrich-Schiller-Universität Jena
Inselplatz 5
07743 Jena
Germany
Ansprechpartner / Contact
Tim Büchner
tim.buechner@uni-jena.de
Klinische Kooperation
Klinik für Hals-Nasen-Ohrenheilkunde
Universitätsklinikum Jena
Technische Realisierung
Rechenzentrum der Friedrich-Schiller-Universität Jena
Diese Anwendung verarbeitet keine personenbezogenen Daten. Es werden ausschließlich Konfigurationsparameter an den Server gesendet, um Renders zu erzeugen; es wird kein Tracking durchgeführt. Vollständiges Impressum und Datenschutz unter inf-cv.uni-jena.de/impressum.
Renders & images
Generated images are licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). You may share and adapt them with attribution to the authors.
Citation
If you use renders in your work, please cite — see the About dialog for the full reference.
3D head model
The underlying 3D anatomical model is commercially licensed and not redistributable. It never leaves the host server. This web interface renders server-side and returns only images to protect those rights. Access to the model files is restricted to authorized users on the host.
Software
The MyoVision source code is © 2026 the authors. Contact the maintainers for licensing terms.