Answers are grounded in this paper and cite their sources.
Computational framework demonstrates accurate brushstroke restoration and style simulation in digital calligraphy, indicating potential for personalized artistic preservation and creation.
The digital preservation and innovative expression of calligraphy and painting styles require accurate modeling of brushstroke morphology, ink diffusion characteristics, and personalized artistic features. To address the limitations of existing digital creation systems in style simulation accuracy and personalized generation capability, this study proposes a brush-and-ink style simulation framework based on generative artificial intelligence. The proposed method integrates deep generative adversarial networks and diffusion models to perform high-dimensional feature encoding, brushstroke parameter modeling, ink-flow representation, and semantic-guided style generation. A human–computer interaction module is further developed to support personalized artistic creation through controllable semantic and stylistic inputs. Experimental evaluation on 5,000 calligraphy and painting samples demonstrates that the proposed framework achieves a brushstroke restoration accuracy of 93.8% and significantly improves style similarity compared with conventional convolutional approaches. The results confirm the effectiveness of generative AI for digital artistic reproduction and personalized creation. The proposed framework also provides methodological references for image generation, visual information processing, and intelligent pattern synthesis applications.
No takes yet. Share an insight, caveat, or question.
Li et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: