Saved in:
Bibliographic Details
Main Authors: Kang, Zejian, Zheng, Kai, Fei, Yuanchen, Yang, Wentao, Zou, Hongyuan, Huang, Xiangru
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.14827
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917350901547008
author Kang, Zejian
Zheng, Kai
Fei, Yuanchen
Yang, Wentao
Zou, Hongyuan
Huang, Xiangru
author_facet Kang, Zejian
Zheng, Kai
Fei, Yuanchen
Yang, Wentao
Zou, Hongyuan
Huang, Xiangru
contents Facial action estimation from a single image is often formulated as predicting or fitting parameters in compact expression spaces, which lack explicit semantic interpretability. However, many practical applications, such as avatar control and human-computer interaction, require interpretable facial actions that correspond to meaningful muscle movements. In this work, we propose SemanticFace, a framework for facial action estimation in the interpretable ARKit blendshape space that reformulates coefficient prediction as structured semantic reasoning. SemanticFace adopts a two-stage semantic distillation paradigm: it first derives structured semantic supervision from ground-truth ARKit coefficients and then distills this knowledge into a multimodal large language model to predict interpretable facial action coefficients from images. Extensive experiments demonstrate that language-aligned semantic supervision improves both coefficient accuracy and perceptual consistency, while enabling strong cross-identity generalization and robustness to large domain shifts, including cartoon faces.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14827
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SemanticFace: Semantic Facial Action Estimation via Semantic Distillation in Interpretable Space
Kang, Zejian
Zheng, Kai
Fei, Yuanchen
Yang, Wentao
Zou, Hongyuan
Huang, Xiangru
Computer Vision and Pattern Recognition
Facial action estimation from a single image is often formulated as predicting or fitting parameters in compact expression spaces, which lack explicit semantic interpretability. However, many practical applications, such as avatar control and human-computer interaction, require interpretable facial actions that correspond to meaningful muscle movements. In this work, we propose SemanticFace, a framework for facial action estimation in the interpretable ARKit blendshape space that reformulates coefficient prediction as structured semantic reasoning. SemanticFace adopts a two-stage semantic distillation paradigm: it first derives structured semantic supervision from ground-truth ARKit coefficients and then distills this knowledge into a multimodal large language model to predict interpretable facial action coefficients from images. Extensive experiments demonstrate that language-aligned semantic supervision improves both coefficient accuracy and perceptual consistency, while enabling strong cross-identity generalization and robustness to large domain shifts, including cartoon faces.
title SemanticFace: Semantic Facial Action Estimation via Semantic Distillation in Interpretable Space
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.14827