EpiAgent: An Agent-Centric System for Ancient Inscription Restoration

arXiv cs.CV / 4/13/2026

📰 NewsIdeas & Deep AnalysisTools & Practical UsageModels & Research

共有:

Key Points

EpiAgent is proposed as an agent-centric system to restore ancient inscriptions by treating restoration as a hierarchical planning problem rather than a rigid single-pass pipeline.
The approach uses an LLM-based central planner operating within an Observe–Conceive–Execute–Reevaluate loop to coordinate multimodal analysis, historical knowledge, specialized restoration tools, and iterative self-refinement.
By leveraging adaptive agent coordination, EpiAgent aims to generalize better across heterogeneous real-world degradation patterns that often break conventional AI restoration workflows.
Experiments on real degraded inscriptions reportedly show improved restoration quality and stronger generalization versus existing methods.
The authors release the code publicly, positioning the work as a step toward more expert-level, agent-driven digital heritage restoration.

Abstract

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.