Deep Unfolding Dehazing Network via Iterative Refinement and Self-Prompted Correction Learning

Existing one-time dehazing approaches struggle to simultaneously restore high-fidelity scene content and suppress haze-induced artifacts. Although recursive iterations can enhance the modeling capacity for complex degradations, the associated estimation errors are often amplified during propagation, thereby constraining the overall dehazing performance. To address these challenges, this work proposes a deep unfolding dehazing network, termed I3-Net, which integrates an iterative refinement strategy (IRS) and self-prompted correction learning (SCL). Specifically, we first develop a baseline dehazing network, termed I-Net, which is constructed around a physically-aware feature enhancement module (PFEM). By embedding physical priors into the feature space, PFEM enforces consistency between learned representations and the haze degradation process, thereby providing a reliable foundation for subsequent refinement. Building upon I-Net, IRS is designed to recursively unfold the baseline, progressively improving its dehazing outputs and enabling the construction of a deep unfolding dehazing network, I3-Net, with cross-stage feature association capability. To mitigate the accumulation of minor estimation errors inherent in iterative frameworks, we further propose SCL mechanism inspired by the corrective behavior of the human visual system. By integrating IRS and SCL, I3-Net adaptively identifies and rectifies residual haze regions at each unfolding stage, effectively suppressing error propagation and achieving high-quality image restoration. Extensive experiments demonstrate that the proposed I3-Net consistently outperforms existing SOTA methods in both quantitative metrics and visual perception across multiple benchmark datasets.