Adaptive Enhancement of Extreme Low-Light Images

TL;DR

This paper introduces a new dataset and a deep learning model for adaptively enhancing extremely low-light images across various intensity levels, overcoming limitations of previous methods that assume known optimal output intensities.

Contribution

The authors created a large low-light image dataset and developed a deep learning model capable of enhancing images with unseen intensity levels at runtime.

Findings

Model effectively enhances images across diverse low-light scenarios

Dataset enables training of adaptive enhancement models

Proposed method outperforms existing approaches in challenging conditions

Abstract

Existing methods for enhancing dark images captured in a very low-light environment assume that the intensity level of the optimal output image is known and already included in the training set. However, this assumption often does not hold, leading to output images that contain visual imperfections such as dark regions or low contrast. To facilitate the training and evaluation of adaptive models that can overcome this limitation, we have created a dataset of 1500 raw images taken in both indoor and outdoor low-light conditions. Based on our dataset, we introduce a deep learning model capable of enhancing input images with a wide range of intensity levels at runtime, including ones that are not seen during training. Our experimental results demonstrate that our proposed dataset combined with our model can consistently and effectively enhance images across a wide range of diverse and challenging scenarios.