Draft, Verify, Restore: Self-Refining Historical Inscription Restoration with a Unified MLLM

Inscriptions are invaluable cultural heritage, yet centuries of degradation (e.g., fractures, erosion, oxidation) have rendered many partially il-legible. Existing Historical Inscription Restoration (HIR) methods rely on task-separated pipelines with irreversible error accumulation and patch-based generation that sacrifices page-level consistency. Therefore, we present Uni-HIR , the first unified MLLM for end-to-end historical inscription restoration. It integrates two novel designs, Draft-Guided Localization and Hierarchical Self-Refinement , to enable accurate damage localization and illegible-content prediction via iterative reasoning and self-correction. This unified approach enables true page-level restoration with consistent ty-pography and style. To support training under high-resolution inputs and long sequences, we design UHIRFactory and construct HIR-Bench , enabling step-wise, memory-efficient instruction tuning with step-aware annotations for intermediate drafts and refinements. Experiments demonstrate that UniHIR achieves superior performance in both text restoration accuracy and appearance restoration quality, validating that HIR can be effectively tack-led by a standalone model in a unified manner. The model and code are available at https://github.com/ZZXF11/UniHIR.