Scholarlink

<p>Chinese painting restoration blends artistic judgment with heritage preservation. Although AI offers new capabilities, existing methods often struggle to reflect the medium’s distinctive stylistic characteristics and to fit restorers’ practical workflows, limiting their usefulness in conservation. To address this gap, we developed InkRenew, an AI-assisted restoration system. Leveraging deep learning, InkRenew integrates dynastic and stylistic knowledge to provide real-time restoration guidance. In a controlled experiment with 34 novice restorers, we compared AI-assisted and traditional workflows in terms of restoration quality, accuracy, and user experience. The results indicate that InkRenew improves efficiency and precision for novice users and reduces perceived operational burden. This work contributes (1) a digital framework that connects AI techniques with traditional restoration knowledge, and (2) an AI-assisted system that supports restorers with real-time guidance, with empirical evidence from a controlled user study. While the study focuses on novice participants in a controlled setting, the findings suggest InkRenew’s potential as a practical aid for restoration tasks.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

From traditional craft to digital restoration: an intelligent rebirth of ancient Chinese painting restoration technique

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月22日

查看全文
  • Ying Zhang,
  • Kewen Zhu,
  • Zejian Li,
  • Zhongni Liu,
  • Kaixin Jia,
  • Jiesi Zhang,
  • Lingyun Sun

摘要

Chinese painting restoration blends artistic judgment with heritage preservation. Although AI offers new capabilities, existing methods often struggle to reflect the medium’s distinctive stylistic characteristics and to fit restorers’ practical workflows, limiting their usefulness in conservation. To address this gap, we developed InkRenew, an AI-assisted restoration system. Leveraging deep learning, InkRenew integrates dynastic and stylistic knowledge to provide real-time restoration guidance. In a controlled experiment with 34 novice restorers, we compared AI-assisted and traditional workflows in terms of restoration quality, accuracy, and user experience. The results indicate that InkRenew improves efficiency and precision for novice users and reduces perceived operational burden. This work contributes (1) a digital framework that connects AI techniques with traditional restoration knowledge, and (2) an AI-assisted system that supports restorers with real-time guidance, with empirical evidence from a controlled user study. While the study focuses on novice participants in a controlled setting, the findings suggest InkRenew’s potential as a practical aid for restoration tasks.