CURE: Controllable Unified Image Restoration for Complex Degradations

2026-07-03

AI Summary

Existing methods struggle to handle the intricate coupling among multiple degradation factors in composite image degradation and lack fine-grained control over the restoration process. To address these limitations, this work proposes CURE, a unified framework that leverages identity embeddings and a mixing ratio mechanism to learn disentangled and adjustable degradation representations, enabling intensity-controllable selective or joint restoration. By incorporating step-wise intermediate losses and a permutation-invariant training strategy, CURE can be seamlessly integrated into existing controllable restoration models without any architectural modifications. Experimental results demonstrate that CURE achieves state-of-the-art performance on composite degradation benchmarks and allows flexible adjustment of the restoration strength for individual degradation components through tunable embedding ratios.

Abstract

The presence of composite degradations poses a significant challenge, since the underlying corruption factors exhibit complex and interdependent interactions. Even when the degradation types are known, accurately restoring the image remains difficult due to the intertwined nature of their effects and the need for selective control during the recovery process. To address this, we introduce CURE, a unified framework that enables controllable restoration in complex degradation settings by learning disentangled and adjustable representations. CURE is driven by four complementary objectives. First, an identity embedding is incorporated, along with a reconstruction constraint, to ensure that the model can reproduce the input image when restoration is unnecessary. Second, the ratio control mechanism blends the identity embedding with degradation-specific embeddings using user-regulated mixing ratios, allowing continuous control over restoration intensity. Third, an intermediate loss is applied to supervise stepwise outputs, each encouraged to tackle the removal of only a single degradation factor within a composite mixture. Finally, a permutation-invariant loss ensures that the model achieves consistent restoration quality regardless of the order in which multiple degradations are addressed. Since CURE modifies only the training strategy and not the underlying network architecture, it can be seamlessly integrated into existing controllable restoration models. Experiments demonstrate that CURE delivers state-of-the-art performance on composite degradation benchmarks, while enabling both selective and jointly fused restoration through flexible modulation of embedding ratios. The code and dataset are available at https://github.com/bo-oseng/CURE.

Problem

• image restoration
• composite degradations
• controllable restoration
• degradation disentanglement
• selective control

Innovation

• controllable restoration
• composite degradations
• disentangled representation
• ratio control
• permutation-invariant loss