Learning to See in the Dark

TL;DR

This paper introduces a new dataset and a learning-based pipeline for low-light image enhancement, demonstrating improved processing of raw sensor data in challenging night-time conditions.

Contribution

It provides a novel dataset of raw low-light images with reference data and develops an end-to-end CNN pipeline that directly processes raw sensor data for better low-light imaging.

Findings

Promising results on the new dataset

Analysis of factors affecting performance

Potential for future improvements

Abstract

Imaging in low light is challenging due to low photon count and low SNR. Short-exposure images suffer from noise, while long exposure can induce blur and is often impractical. A variety of denoising, deblurring, and enhancement techniques have been proposed, but their effectiveness is limited in extreme conditions, such as video-rate imaging at night. To support the development of learning-based pipelines for low-light image processing, we introduce a dataset of raw short-exposure low-light images, with corresponding long-exposure reference images. Using the presented dataset, we develop a pipeline for processing low-light images, based on end-to-end training of a fully-convolutional network. The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. We report promising results on the new dataset, analyze factors that affect performance, and highlight opportunities for future work. The results are shown in the supplementary video at https://youtu.be/qWKUFK7MWvg