Deep Convolutional Denoising of Low-Light Images

TL;DR

This paper introduces a deep convolutional neural network approach for Poisson noise reduction in low-light images, outperforming previous methods in quality and speed, and benefits from class-specific priors.

Contribution

The paper presents a novel deep learning framework for Poisson denoising that surpasses state-of-the-art performance and reduces computational complexity.

Findings

Outperforms previous methods visually and quantitatively

Is significantly faster than prior approaches

Gains additional improvements with class-specific priors

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.