将复杂噪声转为高斯噪声，提升图像去噪泛化能力
Learning to Translate Noise for Robust Image Denoising
- 先将真实噪声转为独立于图像内容的高斯噪声
- 在转换后的噪声上使用预训练模型去噪，性能更稳定
- 适合处理未知真实噪声场景，对工业应用有实用价值
基于深度学习的图像去噪方法在面对分布外的真实世界噪声时往往表现不佳。为此，本文提出一种新型噪声翻译框架：不在原始含噪图像上直接去噪，而是先通过噪声翻译网络将复杂的、未知的真实世界噪声转化为空间不相关且与图像内容无关的高斯噪声。随后，利用一个针对高斯噪声预训练的图像去噪网络对转化后的图像进行处理，从而实现鲁棒且一致的去噪效果。我们基于高斯噪声的数学特性，设计了合理的损失函数和网络结构。实验结果表明，该方法在多个基准测试中显著提升了鲁棒性和泛化能力，优于现有最先进方法。可视化结果及源代码已发布于项目主页。
原文摘要 · Abstract (English)
Deep learning-based image denoising techniques often struggle with poor generalization performance to out-of-distribution real-world noise. To tackle this challenge, we propose a novel noise translation framework that performs denoising on an image with translated noise rather than directly denoising an original noisy image. Specifically, our approach translates complex, unknown real-world noise into Gaussian noise, which is spatially uncorrelated and independent of image content, through a noise translation network. The translated noisy images are then processed by an image denoising network pretrained to effectively remove Gaussian noise, enabling robust and consistent denoising performance. We also design well-motivated loss functions and architectures for the noise translation network by leveraging the mathematical properties of Gaussian noise. Experimental results demonstrate that the proposed method substantially improves robustness and generalizability, outperforming state-of-the-art methods across diverse benchmarks. Visualized denoising results and the source code are available on our project page.
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。