A Research Framework for Controllable Multimodal Visual Design Generation
Journal of Organizational and End User Computing · 10.04.2026 · 38 (1) · 1-29
DOI: 10.4018/joeuc.406954 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Organizational and End User Computing, erschienen am 10.04.2026. Verfasst von Zhenyu Wang und 3 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
Controllable image generation has advanced rapidly with diffusion models, yet existing approaches struggle to integrate multiple heterogeneous control signals and lack mechanisms for enforcing professional design principles. Addressing this challenge requires a unified framework capable of harmonizing semantic, structural, and stylistic modalities while maintaining geometric precision and aesthetic coherence. This study proposes UMC-Design, a unified multimodal controllable framework that introduces a shared control representation, a cross-domain fusion mechanism, and a dual-path diffusion architecture synchronized through a design prior network. The model jointly processes text, vector layouts, semantic maps, and reference images, enabling flexible and scalable multimodal conditioning. Experiments on COCO-Stuff, RICO + PubLayNet, and Crello demonstrate that UMC-Design achieves state-of-the-art performance, reducing FID to 22.3 and improving multimodal alignment to 0.81, surpassing leading baselines by large margins.
Zitieren
APA
Wang, Z., Malik, I., Diao, Z., & Wang, C. (2026). A Research Framework for Controllable Multimodal Visual Design Generation. Journal of Organizational and End User Computing, 38(1), 1-29. https://doi.org/10.4018/joeuc.406954
Vancouver
Wang Z, Malik I, Diao Z, Wang C. A Research Framework for Controllable Multimodal Visual Design Generation. Journal of Organizational and End User Computing. 2026;38(1):1-29. doi:10.4018/joeuc.406954
BibTeX
@article{Wang2026,
author = {Wang, Zhenyu and Malik, Ifrah and Diao, Zhengze and Wang, Chenhao},
title = {A Research Framework for Controllable Multimodal Visual Design Generation},
journal = {Journal of Organizational and End User Computing},
year = {2026},
volume = {38},
number = {1},
pages = {1--29},
doi = {10.4018/joeuc.406954}
}
EUVIMED