Self-supervised Image Enhancement Network: Training with Low Light Images Only

TL;DR

This paper introduces a simple, self-supervised deep learning method for low light image enhancement that trains solely on low light images, achieving state-of-the-art speed and quality without requiring large datasets.

Contribution

A novel maximum entropy based Retinex model enabling training with only low light images, simplifying the process and reducing data dependency.

Findings

Achieves state-of-the-art enhancement quality

Fast training with only low light images

No need for large datasets or paired training data

Abstract

This paper proposes a self-supervised low light image enhancement method based on deep learning. Inspired by information entropy theory and Retinex model, we proposed a maximum entropy based Retinex model. With this model, a very simple network can separate the illumination and reflectance, and the network can be trained with low light images only. We introduce a constraint that the maximum channel of the reflectance conforms to the maximum channel of the low light image and its entropy should be largest in our model to achieve self-supervised learning. Our model is very simple and does not rely on any well-designed data set (even one low light image can complete the training). The network only needs minute-level training to achieve image enhancement. It can be proved through experiments that the proposed method has reached the state-of-the-art in terms of processing speed and effect.