用动态卷积核迭代去噪，小模型也能泛化到多种噪声。
IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising
- 通过动态生成像素级卷积核，自适应局部结构
- 仅用单层高斯噪声训练，却在多类噪声上表现优异
- 模型极小（0.04M），适合实际部署
图像去噪是计算机视觉的基础挑战，广泛应用于摄影和医学成像。尽管基于深度学习的方法取得了显著进展，但其对特定噪声分布的依赖限制了在未见噪声类型和强度下的泛化能力。现有方法虽尝试通过大量训练数据和高计算资源缓解此问题，但仍存在过拟合现象。为此，本文提出一种利用高效运算生成动态卷积核的图像去噪方法，有效防止过拟合并增强对未知噪声的鲁棒性。具体而言，该方法采用特征提取模块获取噪声无关特征，结合全局统计与局部相关性模块捕捉全面的噪声特性与结构关联；随后，核预测模块基于这些线索生成随位置变化的像素级卷积核，并进行迭代应用以实现去噪。该设计兼顾效率与高质量重建。即使仅在单层高斯噪声上训练，紧凑模型（约0.04百万参数）仍能在多种噪声类型和水平下表现优异，展示了迭代动态滤波在实际图像去噪中的潜力。
原文摘要 · Abstract (English)
Image denoising is a fundamental challenge in computer vision, with applications in photography and medical imaging. While deep learning-based methods have shown remarkable success, their reliance on specific noise distributions limits generalization to unseen noise types and levels. Existing approaches attempt to address this with extensive training data and high computational resources but they still suffer from overfitting. To address these issues, we conduct image denoising by utilizing dynamically generated kernels via efficient operations. This approach helps prevent overfitting and improves resilience to unseen noise. Specifically, our method leverages a Feature Extraction Module for robust noise-invariant features, Global Statistics and Local Correlation Modules to capture comprehensive noise characteristics and structural correlations. The Kernel Prediction Module then employs these cues to produce pixel-wise varying kernels adapted to local structures, which are then applied iteratively for denoising. This ensures both efficiency and superior restoration quality. Despite being trained on single-level Gaussian noise, our compact model (~ 0.04 M) excels across diverse noise types and levels, demonstrating the promise of iterative dynamic filtering for practical image denoising.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。