Deep Convolutional Denoising of Low-Light Images

Abstract

Poisson distribution is used for modeling noise in photon-limited imaging. While canonical examples include relatively exotic types of sensing like spectral imaging or astronomy, the problem is relevant to regular photography now more than ever due to the booming market for mobile cameras. Restricted form factor limits the amount of absorbed light, thus computational post-processing is called for. In this paper, we make use of the powerful framework of deep convolutional neural networks for Poisson denoising. We demonstrate how by training the same network with images having a specific peak value, our denoiser outperforms previous state-of-the-art by a large margin both visually and quantitatively. Being flexible and data-driven, our solution resolves the heavy ad hoc engineering used in previous methods and is an order of magnitude faster. We further show that by adding a reasonable prior on the class of the image being processed, another significant boost in performance is achieved.

Cited by in corpus (8)

• Imaging through glass diffusers using densely connected convolutional networks
• End-to-End Denoising of Dark Burst Images Using Recurrent Fully Convolutional Networks
• Characterising lognormal fractional-Brownian-motion density fields with a Convolutional Neural Network
• Very Power Efficient Neural Time-of-Flight
• Low Photon Budget Phase Retrieval with Perceptual Loss Trained Deep Neural Networks
• Dynamic Low-light Imaging with Quanta Image Sensors
• An Integrated Enhancement Solution for 24-hour Colorful Imaging
• Distribution Conditional Denoising: A Flexible Discriminative Image Denoiser