MMDIR：多模态指令驱动的混合退化文档图像复原框架
MMDIR: Multimodal Instruction-Driven Framework for Mixed-Degradation Document Image Restoration
提出用语义结构化指令动态识别混合退化类型（模糊、阴影、文字水印、印章），为文档图像复原提供了一种可复用的多模态条件控制思路；同时发布的 MixedDoc 基准填补了真实混合退化数据集的空白，可用于评估模型在复杂退化下的鲁棒性。
原文依据 we propose MMDIR, a multimodal instruction-driven framework designed for document image restoration under mixed and uncertain degradation conditions.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论复原退化文档图像对于提升视觉质量以及优化下游文档分析任务的性能都至关重要。尽管现有方法在复原效果上已取得显著提升，但它们主要针对单一类型的退化场景。当前方法通常需要为特定退化类型训练多个专用模型，或依赖对退化模式的显式先验知识来指导训练过程。为克服这些局限，我们提出 MMDIR，一种多模态指令驱动的框架，专为混合且不确定退化条件下的文档图像复原而设计。通过利用语义结构化指令，MMDIR 能够动态识别当前存在的退化类型（模糊、阴影、文字水印和印章），同时增强退化感知的表征学习。此外，我们引入了一个名为 MixedDoc 的新基准，包含复杂的混合退化，其中每张图像都包含上述退化类型的随机组合。该基准填补了现有数据集的关键空白——现有数据集缺乏真实的多退化样本，且常常忽略印章和文字水印等常见遮挡物。我们方法在已公开的基准和新建数据集上均得到了充分验证。数据集可在 https://github.com/xiaomore/MMDIR 获取。
英文原文摘要 1439 字符
Restoring degraded document image is essential for both improving visual quality and optimizing performance in downstream document analysis tasks. Although existing methods have demonstrated substantial improvements in restoration outcomes, they primarily address single-type degradation scenarios. Current approaches typically necessitate training multiple specialized models for specific degradation types or rely on explicit prior knowledge of degradation patterns to guide the training process. To overcome these limitations, we propose MMDIR, a multimodal instruction-driven framework designed for document image restoration under mixed and uncertain degradation conditions. By leveraging semantically structured instructions, MMDIR dynamically identifies present degradation types (blur, shadow, text watermark, and seal), while enhancing degradation-aware representation learning. Furthermore, we introduce a novel benchmark named MixedDoc comprising complex mixed degradations, where each image contains randomized combinations of the aforementioned types. This benchmark addresses a critical gap in existing datasets, which lack realistic multi-degradation samples and often overlook common obstructions such as seals and text watermarks. The effectiveness of our approach is thoroughly validated across both released public benchmarks and our newly proposed dataset. The dataset is available at https://github.com/xiaomore/MMDIR.