Modeling and simulation optimization of interactive design systems based on artistic style transfer
International Journal for Simulation and Multidisciplinary Design Optimization · 2026 · 17 · 8
DOI: 10.1051/smdo/2026007 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal for Simulation and Multidisciplinary Design Optimization, online erschienen am 17.03.2026. Verfasst von Lifeng Yan und 3 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper tackles key challenges in interactive design systems: high latency, weak user control, and the aesthetic-function trade-off. We propose an optimization method integrating lightweight generative networks with dynamic modeling. First, a feedforward network architecture based on the MobileNetV3 encoder and the AdaIN (Adaptive Instance Normalization) decoder is designed to achieve millisecond-level style transfer. Second, based on probabilistic state-space modeling theory, a human-machine collaborative state machine is constructed. This Markov decision process describes the transition probabilities of user operation sequences and integrates hard constraints such as readability and layout rationality. Then, a user-system co-simulation framework is proposed. A virtual user behavior simulator generates diverse interaction sequences, driving the NSGA-III (Non-dominated Sorting Genetic Algorithm III) algorithm to perform multi-objective optimization on style quality, response latency, and constraint satisfaction. Experimental results demonstrate significant improvements over baseline methods (AdaIN, WCT 2 ) in the system's consistency of style expression, real-time interaction, and design usability. After 50 generations of optimization, the average FID (Fréchet Inception Distance) value drops from 20.4 to 13.5; the interaction latency decreases from 286 ms to 187 ms; and the constraint violation rate drops from 22.3% to 5.7%, a decrease of 16.6 percentage points, validating the effectiveness of the “modeling-simulation-optimization” methodology. This method achieves a closed-loop collaboration between art generation and engineering design, providing a modeling, simulation, and optimization solution for intelligent interactive design systems.
Zitieren
APA
Yan, L., Zhang, Q., Li, S., & Liu, R. (2026). Modeling and simulation optimization of interactive design systems based on artistic style transfer. International Journal for Simulation and Multidisciplinary Design Optimization, 17, 8. https://doi.org/10.1051/smdo/2026007
Vancouver
Yan L, Zhang Q, Li S, Liu R. Modeling and simulation optimization of interactive design systems based on artistic style transfer. International Journal for Simulation and Multidisciplinary Design Optimization. 2026;17:8. doi:10.1051/smdo/2026007
BibTeX
@article{Yan2026,
author = {Yan, Lifeng and Zhang, Qianyun and Li, Sujun and Liu, Rongrong},
title = {Modeling and simulation optimization of interactive design systems based on artistic style transfer},
journal = {International Journal for Simulation and Multidisciplinary Design Optimization},
year = {2026},
volume = {17},
pages = {8},
doi = {10.1051/smdo/2026007}
}
EUVIMED