SiGnature: Explicit Motion Diffusion for Stylized Semantic Gesture Generation
Computer Graphics Forum · 12.08.2026
DOI: 10.1111/cgf.70557 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 12.08.2026. Verfasst von Adi Rosenthal und 4 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Israel Science Foundation.
Abstract (Originalsprache)
While recent advances in co‐speech gesture generation have achieved impressive rhythmic synchronization, synthesizing gestures that are both semantically meaningful and faithful to a speaker's unique non‐verbal style remains an open challenge. Semantic gestures, such as iconic shapes or deictic pointing, are statistically sparse, making them difficult to learn effectively within standard generative models. We present SiGnature, a framework for Stylized and Semantic Gesture generation that reconciles precise semantic control with high‐fidelity style preservation. Unlike prevalent methods that rely on entangled latent representations, SiGnature operates in an explicit joint‐rotation space. This design enables our core contribution, Joint Motion Integration (JMI), a training‐free inference mechanism capable of injecting any external motion sequence, particularly in‐the‐wild semantic gestures, directly into the diffusion process. JMI automatically identifies the specific “active joints” conveying a semantic action and injects them into the generation, while relying on the diffusion backbone to synthesize the remaining body dynamics, including posture and flow, in accordance with the pre‐learned style of the target speaker. This allows for the plug‐and‐play integration of arbitrary motions, including complex semantic gestures, without retraining or introducing the “Frankenstein” artifacts typical of cut‐and‐paste methods. Extensive experiments and perceptual studies demonstrate that SiGnature offers superior semantic motion control while maintaining smooth and natural co‐speech gesture generation and preserving the distinct characteristics of the speaker, thereby outperforming state‐of‐the‐art baselines.
Förderung
- Israel Science Foundation
Zitieren
APA
Rosenthal, A., Koren, T., Shaked, N., Friedman, D., & Shamir, A. (2026). SiGnature: Explicit Motion Diffusion for Stylized Semantic Gesture Generation. Computer Graphics Forum. https://doi.org/10.1111/cgf.70557
Vancouver
Rosenthal A, Koren T, Shaked N, Friedman D, Shamir A. SiGnature: Explicit Motion Diffusion for Stylized Semantic Gesture Generation. Computer Graphics Forum. 2026. doi:10.1111/cgf.70557
BibTeX
@article{Rosenthal2026,
author = {Rosenthal, Adi and Koren, Tomer and Shaked, Nadav and Friedman, Doron and Shamir, Ariel},
title = {SiGnature: Explicit Motion Diffusion for Stylized Semantic Gesture Generation},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70557}
}
EUVIMED