Probabilistic Noise2Void: Unsupervised Content-Aware Denoising
Probabilistic Noise2Void: Unsupervised Content-Aware Denoising
复制标题
DOI：
10.3389/fcomp.2020.00005
复制
发表时间：
2020-02-19
影响因子：
2.6
通讯作者：
Jug, Florian
中科院分区：
文献类型：
--
作者：
Krull, Alexander;Vicar, Tomas;Jug, Florian
目前，卷积神经网络（cnn）是图像去噪的主要方法。传统上，它们是在成对的图像上进行训练的，而这些图像通常很难用于实际应用。这激发了自我监督训练方法，例如对单个噪声图像进行操作的Noise2Void （N2V）。不幸的是，自监督方法无法与图像对训练的模型竞争。在这里，我们提出了Probabilistic Noise2Void (PN2V)，这是一种训练cnn预测逐像素强度分布的方法。将这些与噪声的适当描述相结合，我们获得了噪声观测和每个像素的真实信号的完整概率模型。我们在公开可用的显微镜数据集上评估了PN2V，在广泛的噪声制度下，并获得了与有监督的最先进方法相比具有竞争力的结果。
Today, Convolutional Neural Networks (CNNs) are the leading method for image denoising. They are traditionally trained on pairs of images, which are often hard to obtain for practical applications. This motivates self-supervised training methods, such as Noise2Void (N2V) that operate on single noisy images. Self-supervised methods are, unfortunately, not competitive with models trained on image pairs. Here, we present Probabilistic Noise2Void (PN2V), a method to train CNNs to predict per-pixel intensity distributions. Combining these with a suitable description of the noise, we obtain a complete probabilistic model for the noisy observations and true signal in every pixel. We evaluate PN2V on publicly available microscopy datasets, under a broad range of noise regimes, and achieve competitive results with respect to supervised state-of-the-art methods.