UniLDiff：释放扩散先验在一体化图像复原中的潜力
UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration
把预训练扩散模型的先验直接搬进一体化图像复原：DAFF 在每个去噪步用解耦融合+自适应调制注入低质特征，DAEM 用专家路由在解码器端补纹理，这套「退化条件注入去噪链」的做法可迁移到其他条件生成式复原任务。
原文依据 we introduce a Degradation-Aware Feature Fusion (DAFF) to dynamically inject low-quality features into each denoising step
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论一体化图像复原（AiOIR）已成为一个有前景但充满挑战的研究方向。为应对多样退化建模与细节保持这两项核心挑战，我们提出 UniLDiff，一个融合退化感知与细节感知机制的统一框架，释放扩散先验的潜力以实现鲁棒的图像复原。具体而言，我们引入退化感知特征融合（DAFF），通过解耦融合与自适应调制将低质量特征动态注入每个去噪步，从而实现对多样且复合退化的隐式建模。此外，我们在解码器中设计了细节感知专家模块（DAEM），通过专家路由增强纹理与精细结构的恢复。在多任务与混合退化设置下的大量实验表明，本方法持续取得最优性能，凸显了扩散先验在统一图像复原中的实际潜力。
英文原文摘要 986 字符
All-in-One Image Restoration (AiOIR) has emerged as a promising yet challenging research direction. To address the core challenges of diverse degradation modeling and detail preservation, we propose UniLDiff, a unified framework enhanced with degradation- and detail-aware mechanisms, unlocking the power of diffusion priors for robust image restoration. Specifically, we introduce a Degradation-Aware Feature Fusion (DAFF) to dynamically inject low-quality features into each denoising step via decoupled fusion and adaptive modulation, enabling implicit modeling of diverse and compound degradations. Furthermore, we design a Detail-Aware Expert Module (DAEM) in the decoder to enhance texture and fine-structure recovery through expert routing. Extensive experiments across multi-task and mixed degradation settings demonstrate that our method consistently achieves state-of-the-art performance, highlighting the practical potential of diffusion priors for unified image restoration.