Supervised deep learning has become the method of choice for image denoising. It involves the training of neural networks on large datasets composed of pairs of noisy and clean images. However, the necessity of training data that are specific to the targeted application constrains the widespread use of denoising networks. Recently, several approaches have been developed to overcome this difficulty by whether artificially generating realistic clean/noisy image pairs, or training exclusively on noisy images. In this paper, we show that, contrary to popular belief, denoising networks specialized in the removal of Gaussian noise can be efficiently leveraged in favor of real-world image denoising, even without additional training. For this to happen, an appropriate variance-stabilizing transform (VST) has to be applied beforehand. We propose an algorithm termed Noise2VST for the learning of such a model-free VST. Our approach requires only the input noisy image and an off-the-shelf Gaussian denoiser. We demonstrate through extensive experiments the efficiency and superiority of Noise2VST in comparison to existing methods trained in the absence of specific clean/noisy pairs.

翻译：监督式深度学习已成为图像去噪的首选方法。该方法通过在由含噪图像与干净图像对构成的大规模数据集上训练神经网络来实现。然而，针对特定应用场景的训练数据需求限制了去噪网络的广泛应用。近期，研究者们通过人工生成逼真的干净/含噪图像对，或仅使用含噪图像进行训练等途径，开发了若干克服此困难的方法。本文证明，与普遍认知相反，专门用于去除高斯噪声的去噪网络即使无需额外训练，也能有效应用于真实世界图像去噪。实现此目标的关键在于预先施加恰当的方差稳定变换（VST）。我们提出一种名为Noise2VST的算法来学习此类无模型VST。该方法仅需输入含噪图像和现成的高斯去噪器即可运行。通过大量实验，我们证明了相较于现有无需特定干净/含噪图像对训练的方法，Noise2VST在效能与优越性方面的显著表现。