Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yuyi, Zhang, Peirong, Yang, Zhenhua, Yan, Pengyu, Shi, Yongxin, Liu, Pengwei, Guo, Fengjun, Jin, Lianwen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.05108
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912494485766144
author Zhang, Yuyi
Zhang, Peirong
Yang, Zhenhua
Yan, Pengyu
Shi, Yongxin
Liu, Pengwei
Guo, Fengjun
Jin, Lianwen
author_facet Zhang, Yuyi
Zhang, Peirong
Yang, Zhenhua
Yan, Pengyu
Shi, Yongxin
Liu, Pengwei
Guo, Fengjun
Jin, Lianwen
contents Historical documents represent an invaluable cultural heritage, yet have undergone significant degradation over time through tears, water erosion, and oxidation. Existing Historical Document Restoration (HDR) methods primarily focus on single modality or limited-size restoration, failing to meet practical needs. To fill this gap, we present a full-page HDR dataset (FPHDR) and a novel automated HDR solution (AutoHDR). Specifically, FPHDR comprises 1,633 real and 6,543 synthetic images with character-level and line-level locations, as well as character annotations in different damage grades. AutoHDR mimics historians' restoration workflows through a three-stage approach: OCR-assisted damage localization, vision-language context text prediction, and patch autoregressive appearance restoration. The modular architecture of AutoHDR enables seamless human-machine collaboration, allowing for flexible intervention and optimization at each restoration stage. Experiments demonstrate AutoHDR's remarkable performance in HDR. When processing severely damaged documents, our method improves OCR accuracy from 46.83% to 84.05%, with further enhancement to 94.25% through human-machine collaboration. We believe this work represents a significant advancement in automated historical document restoration and contributes substantially to cultural heritage preservation. The model and dataset are available at https://github.com/SCUT-DLVCLab/AutoHDR.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05108
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration
Zhang, Yuyi
Zhang, Peirong
Yang, Zhenhua
Yan, Pengyu
Shi, Yongxin
Liu, Pengwei
Guo, Fengjun
Jin, Lianwen
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Historical documents represent an invaluable cultural heritage, yet have undergone significant degradation over time through tears, water erosion, and oxidation. Existing Historical Document Restoration (HDR) methods primarily focus on single modality or limited-size restoration, failing to meet practical needs. To fill this gap, we present a full-page HDR dataset (FPHDR) and a novel automated HDR solution (AutoHDR). Specifically, FPHDR comprises 1,633 real and 6,543 synthetic images with character-level and line-level locations, as well as character annotations in different damage grades. AutoHDR mimics historians' restoration workflows through a three-stage approach: OCR-assisted damage localization, vision-language context text prediction, and patch autoregressive appearance restoration. The modular architecture of AutoHDR enables seamless human-machine collaboration, allowing for flexible intervention and optimization at each restoration stage. Experiments demonstrate AutoHDR's remarkable performance in HDR. When processing severely damaged documents, our method improves OCR accuracy from 46.83% to 84.05%, with further enhancement to 94.25% through human-machine collaboration. We believe this work represents a significant advancement in automated historical document restoration and contributes substantially to cultural heritage preservation. The model and dataset are available at https://github.com/SCUT-DLVCLab/AutoHDR.
title Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2507.05108