Low-Light Image Enhancement by Learning Contrastive Representations in Spatial and Frequency Domains

TL;DR

This paper introduces a contrastive learning approach in both spatial and frequency domains to improve low-light image enhancement, leading to better generalization and image quality.

Contribution

It integrates contrastive learning into an illumination correction network across spatial and frequency domains for enhanced low-light image enhancement.

Findings

Outperforms state-of-the-art methods on LOL and LOL-V2 datasets.

Achieves superior qualitative and quantitative results.

Enhances generalization across various low-light conditions.

Abstract

Images taken under low-light conditions tend to suffer from poor visibility, which can decrease image quality and even reduce the performance of the downstream tasks. It is hard for a CNN-based method to learn generalized features that can recover normal images from the ones under various unknow low-light conditions. In this paper, we propose to incorporate the contrastive learning into an illumination correction network to learn abstract representations to distinguish various low-light conditions in the representation space, with the purpose of enhancing the generalizability of the network. Considering that light conditions can change the frequency components of the images, the representations are learned and compared in both spatial and frequency domains to make full advantage of the contrastive learning. The proposed method is evaluated on LOL and LOL-V2 datasets, the results show that the proposed method achieves better qualitative and quantitative results compared with other state-of-the-arts.