Reconnecting the Broken Civilization: Patchwork Integration of Fragments from Ancient Manuscripts
Yuqing Zhang, Zhou Fang, Xinyu Yang, Shengyu Zhang, Baoyi He, Huaiyong Dou, Junchi Yan, Yongquan Zhang, Fei Wu
摘要
The rich tapestry of human history is often painstakingly pieced together from ancient manuscripts, serving as resilient time capsules of cultural heritage, societal norms, religious tenets, and quotidian life. Unfortunately, the ravages of time, careless preservation, and varied forms of degradation frequently leave us with fragmented relics. The traditional process of reconstructing these fragments is an arduous task, demanding exhaustive manual intervention and a global collaboration among archaeologists. This paper presents a transformative approach to this challenge, harnessing multi-media techniques to restore the connectable fragments of the invaluable Dunhuang scrolls. We curate a unique multimodal dataset of the fragmented Dunhuang manuscripts and architect an innovative three-tiered pipeline to reconstruct these historical scrolls. Our initial stage uses a text-based localization strategy, filtering fragment pairs through text comparison. We then employ a novel self-supervised contour-based pairwise matching framework to overcome the hurdle of limited labeled pairing samples. This process is powered by data augmentation techniques and a Siamese network which determines the most compatible matches. The final stage in our pipeline globally reconstructs the selected fragment pairs with hierarchical clustering, bringing us closer to the original grandeur of the Dunhuang scrolls. Our empirical evaluations reveal that this pipeline exhibits a remarkable success rate in fragment assembly. By addressing this cross-disciplinary challenge, our dataset and pipeline not only contribute to the field of multi-media artificial intelligence but also hold profound implications for sociocultural studies and future explorations into the understanding of ancient cultural history.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
引用它的顶会 Paper2
- Rejoining Precious Artifacts: Efficiently Bone Stick Rejoining Based Massive Fragment Images by Contour, Script, and TextureXingyi Wang, Wen Huang, Mengqiang Hu, Junhui Chen 等AAAI 2026
- ShreddingNet: Coarse-to-Fine Restoration for Multi-Source Shredded ManuscriptsHaoyang Cui, Hao Jiang, Yadong MuCVPR 2026
相关 Paper
- Reviving Mural Art through Generative AI: A Comparative Study of AI-Generated and Hand-Crafted RecreationsShuo Zhao, Yifei Huang, Xiaoyang He, Xin Tong 等CHI 2025 · 被引用 11 次
- Predicting the Original Appearance of Damaged Historical DocumentsZhenhua Yang, Dezhi Peng, Yongxin Shi, Yuyi Zhang 等AAAI 2025 · 被引用 8 次
- Knowledge-Aware Artifact Image Synthesis with LLM-Enhanced Prompting and Multi-Source SupervisionShengguang Wu, Zhenglun Chen, Qi SuACM MM 2024 · 被引用 1 次
- MMFL: Multimodal Fusion Learning for Text-Guided Image InpaintingQing Lin, Bo Yan, Jichun Li, Weimin TanACM MM 2020 · 被引用 22 次
- PhiloGPT: A Philology-Oriented Large Language Model for Ancient Chinese Manuscripts with Dunhuang as Case StudyYuqing Zhang, Baoyi He, Yihan Chen, Hangqi Li 等EMNLP 2024 · 被引用 1 次
