TPGDiff: 基于三级先验引导的图像修复扩散网络
TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration
AI总结：
TPGDiff通过整合降质先验、结构先验和语义先验，实现图像修复的分层引导，提升严重降质区域的重建能力。
摘要：
所有-in-one图像修复旨在通过单一统一模型解决多种退化类型。现有方法通常依赖退化先验指导修复，但难以重建严重退化区域的内容。尽管近期工作利用语义信息促进内容生成，但将其整合到扩散模型浅层往往破坏空间结构（例如，模糊伪影）。为此，我们提出了一种三先验引导扩散（TPGDiff）网络用于统一图像修复。TPGDiff在整个扩散轨迹中整合退化先验，同时在浅层引入结构先验，在深层引入语义先验，实现图像重建的分层互补先验引导。具体而言，我们利用多源结构线索作为结构先验，捕捉细粒度细节并指导浅层表示。为了补充此设计，我们进一步开发了蒸馏驱动的语义提取器，以生成稳健的语义先验，确保在严重退化情况下深层可靠高阶指导。此外，采用退化提取器学习退化感知先验，使扩散过程在所有时间步长上实现阶段自适应控制。在单退化和多退化基准上的广泛实验表明，TPGDiff在多样化的修复场景中实现了优越的性能和泛化能力。我们的项目页面是：https://leoyjtu.github.io/tpgdiff-project.
英文摘要：
All-in-one image restoration aims to address diverse degradation types using a single unified model. Existing methods typically rely on degradation priors to guide restoration, yet often struggle to reconstruct content in severely degraded regions. Although recent works leverage semantic information to facilitate content generation, integrating it into the shallow layers of diffusion models often disrupts spatial structures (\emph{e.g.}, blurring artifacts). To address this issue, we propose a Triple-Prior Guided Diffusion (TPGDiff) network for unified image restoration. TPGDiff incorporates degradation priors throughout the diffusion trajectory, while introducing structural priors into shallow layers and semantic priors into deep layers, enabling hierarchical and complementary prior guidance for image reconstruction. Specifically, we leverage multi-source structural cues as structural priors to capture fine-grained details and guide shallow layers representations. To complement this design, we further develop a distillation-driven semantic extractor that yields robust semantic priors, ensuring reliable high-level guidance at deep layers even under severe degradations. Furthermore, a degradation extractor is employed to learn degradation-aware priors, enabling stage-adaptive control of the diffusion process across all timesteps. Extensive experiments on both single- and multi-degradation benchmarks demonstrate that TPGDiff achieves superior performance and generalization across diverse restoration scenarios. Our project page is: https://leoyjtu.github.io/tpgdiff-project.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
