arXiv：cs.LG（机器学习，全量分类）· Ting Huang, Dongdong Wang, Mingqiu Liang, Siyang Lu·· 14 小时前AI 评分30
超越像素重建：面向低资源满文历史文献的检索引导字形感知修复
Beyond Pixel Reconstruction: Retrieval-Guided Glyph-Aware Restoration for Low-Resource Manchu Historical Documents
AI 导读
针对满文历史文献数字化中严重退化和配对训练数据稀缺的问题，研究者提出检索引导的字形感知修复框架，通过检索相关字形样本为修复过程提供字形级结构指导，突破传统像素级重建的局限。在满文历史文献上的实验表明，该方法在图像修复质量和字形保真度上均优于现有修复方法。
正文
Abstract:Historical Manchu documents preserve invaluable linguistic and cultural heritage, yet their digitization is hindered by severe degradations and the scarcity of paired training data. Existing document restoration methods primarily optimize pixel-level reconstruction, which can produce visually plausible results while failing to preserve the structural identity of Manchu glyphs. To address this limitation, we propose a retrieval-guided glyph-aware restoration framework that goes beyond pixel reconstruction by explicitly incorporating glyph-level structural knowledge. Our method retrieves relevant glyph exemplars to provide structural guidance during restoration and integrates this information into the reconstruction process, improving the recovery of degraded character structures under low-resource conditions. Extensive experiments on Manchu historical documents demonstrate that the proposed approach improves both image restoration quality and glyph-level fidelity compared with existing restoration methods. These results highlight the importance of incorporating character-aware structural priors for reliable restoration of low-resource historical documents.
| Comments: | 8 pages, 7 figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.00315 [cs.CV] |
| (or arXiv:2610.00315v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00315 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dongdong Wang [view email]
[v1]
Tue, 29 Sep 2026 00:38:36 UTC (6,155 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org