EnlightenGAN: Deep Light Enhancement Without Paired Supervision

Yifan JiangXinyu GongDing LiuYu ChengChen FangXiaohui ShenJianchao YangPan ZhouZhangyang Wang

article2019IEEE TIP2,519 citationsIEEE SPS Young Author Best Paper Award

Proposes an unsupervised generative adversarial network that restores low-light images without paired training data by utilizing self-regularized perceptual loss, attention mechanisms, and a dual-discriminator architecture.

Listen

Low-light images often suffer from poor contrast, noise, and uneven exposure, which impairs both human viewing and downstream computer vision systems such as autonomous driving and recognition. Capturing perfectly paired low- and normal-light images of the same scene is impractical, and synthetic pairs frequently fail to match real-world conditions, limiting the effectiveness of supervised deep-learning methods.

The article set out to develop and evaluate an unsupervised approach that enhances low-light images without any paired training data. The authors created EnlightenGAN, a one-path generative adversarial network that learns an unpaired mapping from low-light to normal-light image distributions.

Training relied on a collection of 914 low-light and 1,016 normal-light images drawn from multiple public sources and HDR collections, resized to 600 by 400 pixels. The model incorporates a global-local discriminator pair, a self-regularized perceptual loss that preserves VGG features between input and output, and an attention map derived directly from the input illumination channel. These components were tested through ablation studies and compared against recent methods on standard test sets.

EnlightenGAN produced the best overall NIQE scores across five test collections and ranked highest in a human subjective study of 23 images, with an average rank of 1.78. It avoided the over-exposure artifacts common in LIME and the color distortions seen in RetinexNet and CycleGAN. When applied as preprocessing to the ExDark dataset, it raised top-1 classification accuracy from 22.02 percent to 23.94 percent. A domain-adapted version trained on night-time driving images further suppressed noise and artifacts on previously unseen real-world data.

These results indicate that unpaired training removes the dependency on matched pairs and yields models that generalize more reliably across domains and devices. The approach can therefore support practical deployment in varied lighting conditions without costly data collection.

The authors recommend exploring user-controllable enhancement levels within a single model and combining the method with advances in sensor technology. Further validation on larger and more diverse real-world datasets would strengthen before widespread use. The reported gains rest on specific test collections and the assumption that VGG features remain stable under intensity shifts; performance may vary when these conditions change.

Cover for EnlightenGAN: Deep Light Enhancement Without Paired Supervision

Abstract

Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As one such example, this paper explores the low-light image enhancement problem, where in practice it is extremely challenging to simultaneously take a low-light and a normal-light photo of the same visual scene. We propose a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images. Instead of supervising the learning using ground truth data, we propose to regularize the unpaired training using the information extracted from the input itself, and benchmark a series of innovations for the low-light image enhancement problem, including a global-local discriminator structure, a self-regularized perceptual loss fusion, and attention mechanism. Through extensive experiments, our proposed approach outperforms recent methods under a variety of metrics in terms of visual quality and subjective user study. Thanks to the great flexibility brought by unpaired training, EnlightenGAN is demonstrated to be easily adaptable to enhancing real-world images from various domains. The code is available at \url{this https URL}

Citation

MLA
Jiang, Y., et al. “EnlightenGAN: Deep Light Enhancement Without Paired Supervision”. IEEE Transactions on Image Processing, vol. 30, 2021, pp. 2340–49, https://doi.org/10.1109/TIP.2021.3051462.
APA
Jiang, Y., Gong, X., Liu, D., Cheng, Y., Fang, C., Shen, X., Yang, J., Zhou, P., & Wang, Z. (2021). EnlightenGAN: Deep Light Enhancement Without Paired Supervision. IEEE Transactions on Image Processing, 30, 2340–2349. https://doi.org/10.1109/TIP.2021.3051462
Chicago
Jiang, Y., X. Gong, D. Liu, et al. 2021. “EnlightenGAN: Deep Light Enhancement Without Paired Supervision”. IEEE Transactions on Image Processing 30: 2340–49. https://doi.org/10.1109/TIP.2021.3051462.
Harvard
Jiang, Y. et al. (2021) “EnlightenGAN: Deep Light Enhancement Without Paired Supervision”, IEEE Transactions on Image Processing, 30, pp. 2340–2349. Available at: https://doi.org/10.1109/TIP.2021.3051462.
Vancouver
1. Jiang Y, Gong X, Liu D, Cheng Y, Fang C, Shen X, Yang J, Zhou P, Wang Z (2021) EnlightenGAN: Deep Light Enhancement Without Paired Supervision. IEEE Transactions on Image Processing 30:2340–2349

BibTeX

@article{Jiang_2021, title={EnlightenGAN: Deep Light Enhancement Without Paired Supervision}, volume={30}, ISSN={1941-0042}, url={http://dx.doi.org/10.1109/TIP.2021.3051462}, DOI={10.1109/tip.2021.3051462}, journal={IEEE Transactions on Image Processing}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Jiang, Yifan and Gong, Xinyu and Liu, Ding and Cheng, Yu and Fang, Chen and Shen, Xiaohui and Yang, Jianchao and Zhou, Pan and Wang, Zhangyang}, year={2021}, pages={2340–2349} }
Metadata:Crossref

Source Code

This paper has an official code repository available. Click below to access the source code.

View Repository

Access the Paper

This paper is available from its original source. Click below to access the PDF.

Open PDF