We present a learned unsupervised denoising method for arbitrary types of data, which we explore on images and one-dimensional signals. The training is solely based on samples of noisy data and examples of noise, which -- critically -- do not need to come in pairs. We only need the assumption that the noise is independent and additive (although we describe how this can be extended). The method rests on a Wasserstein Generative Adversarial Network setting, which utilizes two critics and one generator.

中文翻译：

---

基于最优传输的无地面实况去噪

我们针对任意类型的数据提出了一种学习的无监督去噪方法，我们对图像和一维信号进行了探索。训练完全基于噪声数据样本和噪声示例，关键是它们不需要成对出现。我们只需要假设噪声是独立的和可加的（尽管我们描述了如何扩展）。该方法基于 Wasserstein Generative Adversarial Network 设置，该设置使用两个评论家和一个生成器。