EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LatentMag: Self-Supervised 3D Magnification for Micro Expressions via Latent Extrapolation

Mengting Wei, Xingxun Jiang, Haoyu Chen, Yante Li, Guoying Zhao

IEEE Transactions on Affective Computing · 2026-01 · 17 (1) · 942-959

DOI: 10.1109/taffc.2025.3640826 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Affective Computing, 2026-01. Verfasst von Mengting Wei und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EU HORIZON-MSCA-SE-2022, ACMod, Research Council of Finland (former Academy of Finland) Academy Professor project EmotionAI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Micro-expressions (MEs) are subtle and brief facial movements that reveal genuine emotional states but are often imperceptible due to their low intensity. While motion magnification has proven effective for enhancing ME visibility in 2D settings, its extension to 3D remains largely unexplored. In this work, we present LatentMag, the first controllable 3D micro-expression magnification framework. Unlike traditional editing methods that rely on fixed labels or expression targets, our approach models expression intensity as a relative, input-dependent signal. We adopt registered 3D meshes as our representation, enabling vertex-level correspondence and interpretable displacement analysis. To guide magnification, we introduce a geometric prior that models amplification as a spatially adaptive transformation, where the change in pairwise distance between points on the output mesh scales with that observed between the input shapes, ensuring natural, localized deformation. We operationalize this prior in a generative framework by disentangling a latent intensity code, whose extrapolation drives controllable shape amplification. Trained in a self-supervised manner using unlabeled mesh sequences, LatentMag generalizes well to unseen identities and expressions, offering a novel solution that bridges geometric interpretability with realistic 3D expression modeling.

Förderung

  • EU HORIZON-MSCA-SE-2022
  • ACMod
  • Research Council of Finland (former Academy of Finland) Academy Professor project EmotionAI
  • HPC project FaceCanvas
  • Academy research fellow funding
  • University of Oulu & Research Council of Finland Profi 7
  • China Scholarship Council

Zitieren

APA

Wei, M., Jiang, X., Chen, H., Li, Y., & Zhao, G. (2026). LatentMag: Self-Supervised 3D Magnification for Micro Expressions via Latent Extrapolation. IEEE Transactions on Affective Computing, 17(1), 942-959. https://doi.org/10.1109/taffc.2025.3640826

Vancouver

Wei M, Jiang X, Chen H, Li Y, Zhao G. LatentMag: Self-Supervised 3D Magnification for Micro Expressions via Latent Extrapolation. IEEE Transactions on Affective Computing. 2026;17(1):942-959. doi:10.1109/taffc.2025.3640826

BibTeX
@article{Wei2026,
  author = {Wei, Mengting and Jiang, Xingxun and Chen, Haoyu and Li, Yante and Zhao, Guoying},
  title = {LatentMag: Self-Supervised 3D Magnification for Micro Expressions via Latent Extrapolation},
  journal = {IEEE Transactions on Affective Computing},
  year = {2026},
  volume = {17},
  number = {1},
  pages = {942--959},
  doi = {10.1109/taffc.2025.3640826}
}
Kostenlos starten →