Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909724087156736 |
|---|---|
| author | Zhao, Fangmin Zeng, Weichao Li, Zhenhang Yang, Dongbao Li, Binbin Bi, Xiaojun Zhou, Yu |
| author_facet | Zhao, Fangmin Zeng, Weichao Li, Zhenhang Yang, Dongbao Li, Binbin Bi, Xiaojun Zhou, Yu |
| contents | Removing various degradations from damaged documents greatly benefits digitization, downstream document analysis, and readability. Previous methods often treat each restoration task independently with dedicated models, leading to a cumbersome and highly complex document processing system. Although recent studies attempt to unify multiple tasks, they often suffer from limited scalability due to handcrafted prompts and heavy preprocessing, and fail to fully exploit inter-task synergy within a shared architecture. To address the aforementioned challenges, we propose Uni-DocDiff, a Unified and highly scalable Document restoration model based on Diffusion. Uni-DocDiff develops a learnable task prompt design, ensuring exceptional scalability across diverse tasks. To further enhance its multi-task capabilities and address potential task interference, we devise a novel \textbf{Prior \textbf{P}ool}, a simple yet comprehensive mechanism that combines both local high-frequency features and global low-frequency features. Additionally, we design the \textbf{Prior \textbf{F}usion \textbf{M}odule (PFM)}, which enables the model to adaptively select the most relevant prior information for each specific task. Extensive experiments show that the versatile Uni-DocDiff achieves performance comparable or even superior performance compared with task-specific expert models, and simultaneously holds the task scalability for seamless adaptation to new tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04055 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion Zhao, Fangmin Zeng, Weichao Li, Zhenhang Yang, Dongbao Li, Binbin Bi, Xiaojun Zhou, Yu Computer Vision and Pattern Recognition Removing various degradations from damaged documents greatly benefits digitization, downstream document analysis, and readability. Previous methods often treat each restoration task independently with dedicated models, leading to a cumbersome and highly complex document processing system. Although recent studies attempt to unify multiple tasks, they often suffer from limited scalability due to handcrafted prompts and heavy preprocessing, and fail to fully exploit inter-task synergy within a shared architecture. To address the aforementioned challenges, we propose Uni-DocDiff, a Unified and highly scalable Document restoration model based on Diffusion. Uni-DocDiff develops a learnable task prompt design, ensuring exceptional scalability across diverse tasks. To further enhance its multi-task capabilities and address potential task interference, we devise a novel \textbf{Prior \textbf{P}ool}, a simple yet comprehensive mechanism that combines both local high-frequency features and global low-frequency features. Additionally, we design the \textbf{Prior \textbf{F}usion \textbf{M}odule (PFM)}, which enables the model to adaptively select the most relevant prior information for each specific task. Extensive experiments show that the versatile Uni-DocDiff achieves performance comparable or even superior performance compared with task-specific expert models, and simultaneously holds the task scalability for seamless adaptation to new tasks. |
| title | Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.04055 |