EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Research on the construction of intelligent art design system based on multimodal perception and generative AI

Hang Hang, Zhengdong Li

Discover Applied Sciences · 19.08.2025 · 7 (9)

DOI: 10.1007/s42452-025-07513-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Discover Applied Sciences, online erschienen am 19.08.2025. Verfasst von Hang Hang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper introduces an intelligent art design system powered by generative AI to address the cross-modal semantic disconnection in art creation. By integrating symbolic cognitive constraints and dynamic rule injection mechanisms, the system enhances both semantic accuracy and aesthetic quality in generative models. A cultural semantic knowledge graph is developed to map cultural metaphors to visual representations, while a symbolic attention encoder ensures semantic consistency during image generation. Additionally, a differentiable aesthetic rule validator adjusts the output in real-time to optimize the alignment with both artistic intent and aesthetic standards. Experimental results show that the proposed system outperforms existing models in key areas such as cultural symbol mapping (92.5% coverage), symmetry, and color harmony, delivering more accurate and aesthetically pleasing results. The system has been applied in real-world art creation, significantly improving the efficiency and creativity of artists by providing culturally relevant and visually coherent references. The findings highlight the system’s potential as an innovative tool for generative art, bridging the gap between semantic accuracy and aesthetic quality in the creative process. Enhanced Semantic and Aesthetic Integration: By embedding symbolic constraints into the diffusion model and using real-time aesthetic validation, our system achieves high accuracy in semantic mapping and meets aesthetic standards, offering an interpretable framework for art generation. Innovative System Design: We designed an intelligent art system that integrates symbolic constraints and dynamic rules, effectively solving cross-modal semantic issues in AI art creation by combining cultural semantics with aesthetic rules. Proven Efficiency and Stability: Experiments show our method excels in parsing cultural metaphors (82.5-85.5% accuracy), visual element mapping (92.5% coverage in cultural symbols), and aesthetic metrics (e.g., symmetry score 0.89), proving its efficiency and stability in multi-modal art generation.

Zitieren

APA

Hang, H., & Li, Z. (2025). Research on the construction of intelligent art design system based on multimodal perception and generative AI. Discover Applied Sciences, 7(9). https://doi.org/10.1007/s42452-025-07513-0

Vancouver

Hang H, Li Z. Research on the construction of intelligent art design system based on multimodal perception and generative AI. Discover Applied Sciences. 2025;7(9). doi:10.1007/s42452-025-07513-0

BibTeX
@article{Hang2025,
  author = {Hang, Hang and Li, Zhengdong},
  title = {Research on the construction of intelligent art design system based on multimodal perception and generative AI},
  journal = {Discover Applied Sciences},
  year = {2025},
  volume = {7},
  number = {9},
  doi = {10.1007/s42452-025-07513-0}
}
Kostenlos starten →