Manchu manuscript restoration improves by avoiding overcorrection
Think Before You Restore: Risk-Aware Manchu Manuscript Restoration with Stroke-Guided Attention
Computer Vision and Pattern RecognitionArtificial IntelligenceMachine Learning
Summary
Restoring old Manchu manuscripts is hard because parts are damaged while other parts are still intact and delicate. The authors created a method that first decides which areas actually need fixing and then carefully restores only those parts. This approach helps keep the original writing intact and prevents unnecessary changes. Their method showed better results in fixing damaged areas while preserving the rest of the manuscript.
What this means in practice
- •For digital archivists: Improve restoration of fragile historical manuscripts by selectively repairing only damaged regions, preserving original content.
- •For cultural heritage preservation teams: Restore scanned images of fragile manuscripts more accurately by avoiding alterations to intact strokes using stroke-guided attention models.
Authors
Mingqiu Liang, Dongdong Wang, Siyang Lu, Ting Huang, Yingjun Qi
Abstract
Full-page blind restoration of historical Manchu manuscripts is challenging due to scarce annotations, unknown degradation regions, and fragile connected strokes. Generic restoration models may improve visual quality but often modify intact content, leading to over-restoration. We propose SAGE-Restore (Stroke-Aware Gated rEstoration), a selective restoration framework that first assesses where restoration is needed and then uses this assessment to guide restoration candidate generation and pixel-level selection. Its encoder predicts patch-level repair probabilities from complementary appearance and stroke-structural cues to condition restoration candidate generation, while the corresponding repair logits are refined into a pixel-level soft gate that selectively controls where the restoration candidate is applied. We further introduce a fidelity-aware evaluation protocol that jointly measures degraded-region recovery, intact-content preservation, and their balance. SAGE-Restore achieves the highest R-Recovery (0.463) and RFS (0.626), while maintaining high U-Fidelity (0.968), demonstrating an effective balance between restoration and content preservation.