Probabilistic Noise2Void: Unsupervised Content-Aware Denoising

Abstract

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.

8 pages, 2 figures

References in corpus (1)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Cited by in corpus (7)

• Self-supervised learning of hologram reconstruction using physics consistency
• Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement
• Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer
• Optimal Transport for Unsupervised Denoising Learning
• Harnessing Artificial Intelligence To Reduce Phototoxicity in Live Imaging
• ENSURE: A General Approach for Unsupervised Training of Deep Image Reconstruction Algorithms
• SelfReDepth: Self-Supervised Real-Time Depth Restoration for Consumer-Grade Sensors