My research focuses on computer vision and multimodal learning for cultural heritage applications, particularly in the analysis, restoration, and generation of Thangka artworks. I explore methods such as diffusion models, cross-modal retrieval, and style transfer to support the digital preservation and understanding of traditional Tibetan art.
My research focuses on computer vision and multimodal learning for cultural heritage applications, particularly in the analysis, restoration, and generation of Thangka artworks. I explore methods such as diffusion models, cross-modal retrieval, and style transfer to support the digital preservation and understanding of traditional Tibetan art.