Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.19593 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911402568974336 |
|---|---|
| author | Arnaud, Estèphe Daoudi, Mohamed Guerreschi, Pierre |
| author_facet | Arnaud, Estèphe Daoudi, Mohamed Guerreschi, Pierre |
| contents | Botulinum toxin (Botox) injections are the gold standard for managing facial asymmetry and aesthetic rejuvenation, yet determining the optimal dosage remains largely intuitive, often leading to suboptimal outcomes. We propose a localized latent editing framework that simulates Botulinum Toxin injection effects for injection planning through dose-response modeling. Our key contribution is a Region-Specific Latent Axis Discovery method that learns localized muscle relaxation trajectories in StyleGAN2's latent space, enabling precise control over specific facial regions without global side effects. By correlating these localized latent trajectories with injected toxin units, we learn a predictive dose-response model. We rigorously compare two approaches: direct metric regression versus image-based generative simulation on a clinical dataset of N=360 images from 46 patients. On a hold-out test set, our framework demonstrates moderate-to-strong structural correlations for geometric asymmetry metrics, confirming that the generative model correctly captures the direction of morphological changes. While biological variability limits absolute precision, we introduce a hybrid "Human-in-the-Loop" workflow where clinicians interactively refine simulations, bridging the gap between pathological reconstruction and cosmetic planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_19593 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Localized Latent Editing for Dose-Response Modeling in Botulinum Toxin Injection Planning Arnaud, Estèphe Daoudi, Mohamed Guerreschi, Pierre Computer Vision and Pattern Recognition Botulinum toxin (Botox) injections are the gold standard for managing facial asymmetry and aesthetic rejuvenation, yet determining the optimal dosage remains largely intuitive, often leading to suboptimal outcomes. We propose a localized latent editing framework that simulates Botulinum Toxin injection effects for injection planning through dose-response modeling. Our key contribution is a Region-Specific Latent Axis Discovery method that learns localized muscle relaxation trajectories in StyleGAN2's latent space, enabling precise control over specific facial regions without global side effects. By correlating these localized latent trajectories with injected toxin units, we learn a predictive dose-response model. We rigorously compare two approaches: direct metric regression versus image-based generative simulation on a clinical dataset of N=360 images from 46 patients. On a hold-out test set, our framework demonstrates moderate-to-strong structural correlations for geometric asymmetry metrics, confirming that the generative model correctly captures the direction of morphological changes. While biological variability limits absolute precision, we introduce a hybrid "Human-in-the-Loop" workflow where clinicians interactively refine simulations, bridging the gap between pathological reconstruction and cosmetic planning. |
| title | Localized Latent Editing for Dose-Response Modeling in Botulinum Toxin Injection Planning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.19593 |