用扩散模型统一修复多种图像退化，提升细节还原能力。
UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration
- 通过动态融合低质量特征，隐式建模复杂退化
- 在多任务和混合退化场景下达到当前最佳性能
- 适合需要统一修复多种图像问题的研究者
全功能图像修复（AiOIR）成为有前景但具挑战性的研究方向。为应对退化建模多样性和细节保留的核心难题，我们提出UniLDiff，一种增强退化与细节感知机制的统一框架，释放扩散先验在鲁棒图像修复中的潜力。具体而言，引入退化感知特征融合（DAFF），通过解耦融合与自适应调制，在每个去噪步骤中动态注入低质量特征，实现对多样化及复合退化的隐式建模。此外，在解码器中设计细节感知专家模块（DAEM），通过专家路由增强纹理与细结构恢复。在多任务及混合退化设置下的大量实验表明，该方法持续取得最优表现，凸显扩散先验在统一图像修复中的实用价值。代码将开源。
原文摘要 · Abstract (English)
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. Our code will be released.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。