EnlightenGAN: Deep Light Enhancement Without Paired Supervision

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 challeng...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on image processing Ročník 30; s. 2340 - 2349
Hlavní autoři: Jiang, Yifan, Gong, Xinyu, Liu, Ding, Cheng, Yu, Fang, Chen, Shen, Xiaohui, Yang, Jianchao, Zhou, Pan, Wang, Zhangyang
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Adaptation models
Gallium nitride
Generative adversarial networks
Ground truth
Image enhancement
Image restoration
Light
Lighting
Low-light enhancement
Training
Training data
unsupervised learning
Visualization
ISSN:1057-7149, 1941-0042, 1941-0042
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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 the 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. Our codes and pre-trained models are available at: https://github.com/VITA-Group/EnlightenGAN .
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2021.3051462