Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains underexplored. To address this gap, we propose a Simultaneous Learning Knowledge Distillation (SLKD) framework tailored for model compression in image restoration tasks. SLKD employs a dual-teacher, single-student architecture with two distinct learning strategies: Degradation Removal Learning (DRL) and Image Reconstruction Learning (IRL), simultaneously. In DRL, the student encoder learns from Teacher A to focus on removing degradation factors, guided by a novel BRISQUE extractor. In IRL, the student decoder learns from Teacher B to reconstruct clean images, with the assistance of a proposed PIQE extractor. These strategies enable the student to learn from degraded and clean images simultaneously, ensuring high-quality compression of image restoration models. Experimental results across five datasets and three tasks demonstrate that SLKD achieves substantial reductions in FLOPs and parameters, exceeding 80%, while maintaining strong image restoration performance.

Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity—manifested in elevated FLOPs and parameter counts—limits their application in real-world scenarios. Existing knowledge distillation methods in image restoration typically employ lightweight student models that directly mimic the intermediate features and reconstruction results of the teacher, overlooking the implicit attention relationships between them. To address this, we propose a Soft Knowledge Distillation (SKD) strategy that incorporates a Multi-dimensional Cross-net Attention (MCA) mechanism for compressing image restoration models. This mechanism facilitates interaction between the student and teacher across both channel and spatial dimensions, enabling the student to implicitly learn the attention matrices. Additionally, we employ a Gaussian kernel function to measure the distance between student and teacher features in kernel space, ensuring stable and efficient feature learning. To further enhance the quality of reconstructed images, we replace the commonly used L1 or KL divergence loss with a contrastive learning loss at the image level. Experiments on three tasks—image deraining, deblurring, and denoising—demonstrate that our SKD strategy significantly reduces computational complexity while maintaining strong image restoration capabilities.

Images captured in outdoor scenes are often simultaneously affected by multiple degradation factors, making robust image restoration critical. To address this challenge, we introduce RMTD (Robust Multi-Type Degradation Dataset), the first comprehensive large-scale dataset specifically designed for outdoor image restoration under diverse degradation conditions. RMTD spans 10 outdoor scene categories and incorporates 8 common degradation types, reflecting real-world challenges. The dataset features 48,000 synthetic multi-degraded images paired with high-quality ground truth, making it the largest benchmark for multi-degraded image restoration. Additionally, 200 real-world multi-degraded images offer authentic test cases for evaluating model robustness under outdoor conditions. To support downstream applications, RMTD provides annotations for over 3,000 objects across 10 categories, facilitating evaluations for tasks such as object detection. Experiments on synthetic and real multi-degraded images demonstrate that models trained on RMTD achieve improvements of 1.31 in PSNR and 0.835 in BRISQUE over existing datasets, proving its robustness as a benchmark for advancing image restoration research. RMTD is available at: https://github.com/ICME25/RMTD.

Restoring real-world images suffering from complex degradations like haze, rain, and blur is a significant challenge. Existing models face difficulties when applied to these real-world images, mainly due to the domain gap between synthetically generated and authentic degradations. In this paper, we propose SDA-Net, a well-designed Semi-supervised Domain Adaptation Network that can effectively restore real-world images. Our method combines the advantages of two foundation models. The supervised knowledge transfer model helps a student network learn from diverse restoration networks, while the unsupervised domain adaptation models guide the student network to generalize from synthetic scenes to real-world scenes. Furthermore, we propose a grained-friendly contrastive learning loss to force our models to retain background details and clear representation. Extensive experiments demonstrate that our SDA-Net outperforms state-of-the-art algorithms on three common real-world datasets with various degradations, achieving a significant improvement of 2.7 scores on BRISQUE and 11.6 scores on PIQE.

Image enhancement methods leveraging learning-based approaches have demonstrated impressive results when trained on synthetic degraded-clear image pairs. However, when deployed in real-world scenarios, such models often suffer significant performance degradation due to the inherent domain gap between synthetic and real degradations. To bridge this gap, we propose a novel Two-stage Contrastive Domain Adaptation image Enhancement (TCDAE) framework consisting of two key strategies: (1) Synthetic-to-Real Domain Transfer Learning (S2R-DTL) that effectively translates images from the synthetic degraded domain to the real degraded domain, aligning the domains at the pixel level, and (2) Degraded-to-Clear Domain Transfer Learning (D2C-DTL) that further adapts the enhancement model from the synthetic to the real domain by translating images from the real degraded domain to the real clean domain in both supervised and unsupervised branches. A unique aspect of our approach is the integration of a Domain Noise Contrastive Estimation (DoNCE) loss in both learning strategies. This specialized loss formulation enables TCDAE to robustly translate images across domains, even in scenarios lacking strong positive examples. Consequently, our framework can generate enhanced images with natural, realistic appearances akin to real clear images. Comprehensive experiments on real-world degraded scenes across diverse tasks, including dehazing, deraining, and deblurring, demonstrate the superiority of TCDAE over state-of-the-art methods, achieving improved visual quality, quantitative metrics, and downstream task performance.