Low-Light Image and Video Enhancement Using Deep Learning: A Survey

TL;DR

This survey comprehensively reviews deep learning methods for low-light image and video enhancement, introduces a new dataset and online platform for evaluation, and assesses their effectiveness in improving perception and face detection in dark conditions.

Contribution

It provides a detailed taxonomy of algorithms, introduces a new diverse dataset and an online evaluation platform, and evaluates existing methods' generalization and performance.

Findings

Deep learning methods significantly improve low-light image quality.

The new dataset captures diverse illumination conditions and camera types.

The online platform enables easy comparison of LLIE techniques.

Abstract

Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. Recent advances in this area are dominated by deep learning-based solutions, where many learning strategies, network structures, loss functions, training data, etc. have been employed. In this paper, we provide a comprehensive survey to cover various aspects ranging from algorithm taxonomy to open issues. To examine the generalization of existing methods, we propose a low-light image and video dataset, in which the images and videos are taken by different mobile phones' cameras under diverse illumination conditions. Besides, for the first time, we provide a unified online platform that covers many popular LLIE methods, of which the results can be produced through a user-friendly web interface. In addition to qualitative and quantitative evaluation of existing methods on publicly available and our proposed datasets, we also validate their performance in face detection in the dark.This survey together with the proposed dataset and online platform could serve as a reference source for future study and promote the development of this research field. The proposed platform and dataset as well as the collected methods, datasets, and evaluation metrics are publicly available and will be regularly updated.