arXiv 2604.093672026-05-27cs.CV

EpiAgent: 一种以智能体为中心的古铭文修复系统

EpiAgent: An Agent-Centric System for Ancient Inscription Restoration

School of Computer Science and Engineering, Southeast University, China（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其跨学科应用关键实验室（东南大学），教育部，中国）；Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China（计算机网络与信息集成关键实验室（东南大学），教育部，中国）；Nanjing University Museum, Nanjing University, China（南京大学博物馆，南京大学，中国）；The China Centre for Linguistic and Strategic Studies, Nanjing University, China（中国语言战略研究中心，南京大学，中国）

Shipeng Zhu, Ang Chen, Na Nie, Pengfei Fang, Min-Ling Zhang, Hui Xue

备注：: Accepted by CVPR 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出基于智能体的EpiAgent系统，通过分层规划与LLM协调多模态分析、历史经验和专用工具，实现灵活自适应的古铭文修复，在真实退化铭文上取得更优修复质量和泛化能力。

摘要：

古铭文作为文化记忆的载体，历经数世纪的环境和人为退化。恢复其交织的视觉和文本完整性是数字遗产保护中最具挑战性的任务之一。然而，现有基于AI的方法通常依赖刚性流水线，难以泛化到如此复杂和异质的真实退化场景。受人类金石学家技能协调工作流程的启发，我们提出EpiAgent，一个以智能体为中心的系统，将铭文修复形式化为分层规划问题。遵循观察-构思-执行-重新评估范式，基于LLM的中央规划器协调多模态分析、历史经验、专用修复工具和迭代自我精炼之间的协作。这种以智能体为中心的协调使得修复过程比传统的单次通过方法更加灵活和自适应。在真实退化的铭文上，EpiAgent相比现有方法实现了更优的修复质量和更强的泛化能力。我们的工作标志着向专家级智能体驱动的文化遗产修复迈出了重要一步。代码可在 https://github.com/blackprotoss/EpiAgent 获取。

英文摘要：

Ancient inscriptions, as repositories of cultural memory, have suffered from centuries of environmental and human-induced degradation. Restoring their intertwined visual and textual integrity poses one of the most demanding challenges in digital heritage preservation. However, existing AI-based approaches often rely on rigid pipelines, struggling to generalize across such complex and heterogeneous real-world degradations. Inspired by the skill-coordinated workflow of human epigraphers, we propose EpiAgent, an agent-centric system that formulates inscription restoration as a hierarchical planning problem. Following an Observe-Conceive-Execute-Reevaluate paradigm, an LLM-based central planner orchestrates collaboration among multimodal analysis, historical experience, specialized restoration tools, and iterative self-refinement. This agent-centric coordination enables a flexible and adaptive restoration process beyond conventional single-pass methods. Across real-world degraded inscriptions, EpiAgent achieves superior restoration quality and stronger generalization compared to existing methods. Our work marks an important step toward expert-level agent-driven restoration of cultural heritage. The code is available at https://github.com/blackprotoss/EpiAgent.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。