DocPure：基于退化感知结构引导的小波调制的无提示统一文档复原
DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation
- College of Computer Science and Artificial Intelligence, Wenzhou University（温州大学计算机与人工智能学院）
- AI Analytics Team, Nasdaq（纳斯达克人工智能分析团队）
- vivo Mobile Communication Co., Ltd（维沃移动通信有限公司）
- College of Engineering and Computer Science, The Australian National University（澳大利亚国立大学工程与计算机科学学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出无提示统一文档复原框架DocPure，通过退化感知结构自编码器与结构引导小波交互机制，在多类文档退化复原任务中实现优于现有方法的性能。
AI中文摘要：
高质量文档图像对信息归档和下游自动处理至关重要，但在非受控采集与传输过程中常受各类退化影响。虽已有统一文档复原技术用于修复多种退化图像，却存在需训练多个退化特定模型、依赖手动任务特定提示或跨任务数据配对的局限。为解决这些问题，本文提出DocPure，一种无提示统一框架，可实现退化感知的文档复原。我们设计了带退化感知路由正则化的退化感知结构自编码器，从退化输入预测干净结构先验；该模型推理时无提示，退化标签仅在训练时作为路由正则化的辅助监督。此外，我们引入结构引导的小波交互机制，连接频域特征与空间语义，其中跨频自适应调制利用低频子带调制高频复原，确保结构一致性。大量实验表明，DocPure在去模糊、去噪、压缩伪影减少、去阴影等各类任务中，较现有最优方法表现出色。
英文摘要：
High-quality document images are pivotal for information archiving and downstream automatic processing. However, they are frequently compromised by diverse degradations during uncontrolled acquisition and transmission. While unified document restoration techniques have been proposed to restore images from multiple degradations, they often struggle with training multiple degradation-specific models, reliance on manual task-specific prompts, or cross-task data pairing. To address these limitations, we propose DocPure, a prompt-free unified framework that achieves degradation-aware document restoration. We design a degradation-aware structure auto-encoder with degradation-informed routing regularization to predict clean structural priors from degraded inputs. The model is prompt-free at inference, and degradation labels are only used as auxiliary supervision for the routing regularization during training. Furthermore, we introduce a structure-guided wavelet interaction mechanism to bridge frequency-domain features and spatial semantics. Within the structure-guided wavelet interaction mechanism, a cross-frequency adaptive modulation utilizes low-frequency sub-bands to modulate high-frequency recovery, ensuring structural consistency. Extensive experiments demonstrate that DocPure achieves strong performance compared with state-of-the-art methods across various tasks, including deblurring, denoising, compression artifact reduction, and deshadowing.
