Adaptive Enhancement of Extreme Low-Light Images

Evgeny Hershkovitch Neiterman

Michael Klyuchka

Gil Ben-Artzi

Computer Science Department, Ariel University, Israel

Dataset+Code

Tune optimal input and output exposures

Output 1

Output 2

Output 3

Highlights

A dataset of 1500 raw images captured in both outdoor and indoor scenes, with five different exposure levels of 0.1s,0.5s,1s,5s and 10s.
A model that can enhance dark images.
Using our model, we are able to output images with varying intensities and adjust the enhancement accordingly without the need for retraining.

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.

Network Architecture - Brightness and ISP Tuning Parameters

One Trained Model - Many Enhancement Options at Inference Time

The Dataset

The top two rows are images from outdoor scenes and the bottom two rows are images from indoor scenes.
Left to right are exposure times of 0.1s,0.5s,1s,5s,10s.

Paper

Adaptive Enhancement of Extreme Low-Light Images,
E.H Neiterman, M. Klyuchka and G. Ben-Artzi
arXiv