Towards All-in-One Image Restoration with Unpaired Training

All-in-one (AIO) image restoration (IR) is crucial for addressing the diverse and complex degradations in real-world scenarios. However, existing AIO IR models are primarily trained with synthetic paired supervision and therefore suffer from severe domain limitations when applied to real-world data. Unpaired learning offers a promising alternative but introduces a significant challenge: removing degradations while faithfully preserving image content without pixel-level paired supervision. This challenge is further amplified in the AIO IR setting. To address it, we propose UADiff, an unpaired AIO IR framework that fine-tunes a pre-trained diffusion model into a one-step restoration backbone. Specifically, UADiff resolves two fundamental issues: degradation adaptation and unpaired constraint. For degradation adaptation, we design a Degradation-Aware Prompt Learning (DAPL) module leveraging SigLIP to learn a set of textual prompts representing degradation and clean concepts. These prompts identify degradations and guide a Degradation-Conditional Low-Rank Adaptation (LoRA) module, achieving degradation-adaptive restoration. For the unpaired constraint, we propose Content-Preserving Regularization (CPR), which promotes contrastive learning on degradation-invariant content features and guides the restored results away from degradation concepts. Extensive experiments demonstrate that UADiff achieves superior restoration performance and generalization, establishing a competitive baseline for unpaired AIO IR in real-world scenarios.