Despite recent advances, developing general-purpose universal denoising and artifact-removal networks remains largely an open problem: Given fixed network weights, one inherently trades-off specialization at one task (e.g., removing Poisson noise) for performance at another (e.g., removing speckle noise). In addition, training such a network is challenging due to the curse of dimensionality: As one increases the dimensions of the specification-space (i.e., the number of parameters needed to describe the noise distribution) the number of unique specifications one needs to train for grows exponentially. Uniformly sampling this space will result in a network that does well at very challenging problem specifications but poorly at easy problem specifications, where even large errors will have a small effect on the overall mean squared error. In this work we propose training denoising networks using an adaptive-sampling/active-learning strategy. Our work improves upon a recently proposed universal denoiser training strategy by extending these results to higher dimensions and by incorporating a polynomial approximation of the true specification-loss landscape. This approximation allows us to reduce training times by almost two orders of magnitude. We test our method on simulated joint Poisson-Gaussian-Speckle noise and demonstrate that with our proposed training strategy, a single blind, generalist denoiser network can achieve peak signal-to-noise ratios within a uniform bound of specialized denoiser networks across a large range of operating conditions. We also capture a small dataset of images with varying amounts of joint Poisson-Gaussian-Speckle noise and demonstrate that a universal denoiser trained using our adaptive-sampling strategy outperforms uniformly trained baselines.

中文翻译：

---

用于盲多分布噪声消除的可扩展训练策略


尽管最近取得了进展，但开发通用的通用去噪和伪影去除网络在很大程度上仍然是一个悬而未决的问题：给定固定的网络权重，一个网络本质上会牺牲一项任务的专业化（例如，去除泊松噪声）来换取另一项任务的性能（例如，去除散斑噪声）。此外，由于维度的诅咒，训练这样的网络是具有挑战性的：随着规范空间维度的增加（即描述噪声分布所需的参数数量），需要训练的唯一规范的数量呈指数级增长。对这个空间进行统一采样将导致一个网络在非常具有挑战性的问题规范下表现良好，但在简单的问题规范下表现不佳，在这种情况下，即使是较大的误差也会对整体均方误差产生很小的影响。在这项工作中，我们提出了使用自适应采样/主动学习策略来训练去噪网络。我们的工作改进了最近提出的通用降噪器训练策略，将这些结果扩展到更高的维度，并结合了真实规格损失景观的多项式近似。这种近似值使我们能够将训练时间减少近两个数量级。我们在模拟的联合泊松-高斯-斑点噪声上测试了我们的方法，并证明通过我们提出的训练策略，单个盲的通才降噪器网络可以在大范围的工作条件下在专用降噪器网络的统一范围内实现峰值信噪比。 我们还捕获了一个包含不同数量联合泊松-高斯-斑点噪声的小型图像数据集，并证明使用我们的自适应采样策略训练的通用降噪器优于统一训练的基线。