主要从事模式识别、计算机视觉与艺术之间的交叉领域，聚焦创新艺术表达形式，为教育、文化遗传保护以及交互设计提供新思路。具体研究包括：

1）智能体交互视觉艺术创作

2）多风格Sketch视觉图像生成

2）基于多模态语义引导的古代书画、壁画虚拟复原关键技术研究 

4）传统山水画、壁画等数字文化遗产活化利用（多模态驱动视频生成）

My research primarily focuses on interdisciplinary areas bridging pattern recognition, computer vision, and art, aiming to pioneer innovative forms of artistic expression and provide novel insights for education, cultural heritage preservation, and interactive design. Specific research topics include:

1)  Agent-Interactive Visual Art Creation  

2)  Multi-Style Sketch-Based Visual Image Generation  

3)  Key Technologies for Multimodal Semantic-Guided Virtual Restoration of Ancient Calligraphy/Paintings and Murals  

4)  Revitalization and Utilization of Digital Cultural Heritage (e.g., Traditional Landscape Paintings, Murals) via Multimodal-Driven Video Generation