🤖 AI Summary
Real-world image denoising faces dual challenges: poor generalizability of handcrafted priors and the heavy reliance of deep learning methods on large-scale paired noisy-clean training data. To address this, we propose Net2Net—a novel framework that, for the first time, seamlessly integrates unsupervised Deep Image Prior (DIP) with a supervised pre-trained denoiser (DRUNet) under a unified Denoising-based Regularization (RED) optimization scheme, requiring no paired annotations. Net2Net synergistically leverages the input-specific modeling capability of untrained networks and the rich noise statistics encoded in large-scale pre-trained models, achieving strong generalization across diverse noise types and imaging conditions without compromising inference efficiency. Extensive experiments on multiple real-world denoising benchmarks demonstrate that Net2Net significantly outperforms existing state-of-the-art methods—especially under extreme data scarcity—while maintaining lightweight deployment.
📝 Abstract
Traditional denoising methods for noise removal have largely relied on handcrafted priors, often perform well in controlled environments but struggle to address the complexity and variability of real noise. In contrast, deep learning-based approaches have gained prominence for learning noise characteristics from large datasets, but these methods frequently require extensive labeled data and may not generalize effectively across diverse noise types and imaging conditions. In this paper, we present an innovative method, termed as Net2Net, that combines the strengths of untrained and pre-trained networks to tackle the challenges of real-world noise removal. The innovation of Net2Net lies in its combination of unsupervised DIP and supervised pre-trained model DRUNet by regularization by denoising (RED). The untrained network adapts to the unique noise characteristics of each input image without requiring labeled data, while the pre-trained network leverages learned representations from large-scale datasets to deliver robust denoising performance. This hybrid framework enhances generalization across varying noise patterns and improves performance, particularly in scenarios with limited training data. Extensive experiments on benchmark datasets demonstrate the superiority of our method for real-world noise removal.