Probabilistic Noise2Void: Unsupervised Content-Aware Denoising
This addresses the challenge of obtaining paired images for denoising in practical applications like microscopy, offering an unsupervised alternative that is competitive with supervised methods, though it is incremental as it builds on existing self-supervised approaches.
The paper tackled the problem of image denoising without paired training data by introducing Probabilistic Noise2Void (PN2V), which trains CNNs to predict per-pixel intensity distributions and combines them with noise descriptions to form a probabilistic model, achieving competitive results with supervised state-of-the-art methods on microscopy datasets across various noise regimes.
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.