EnlightenGAN: Deep Light Enhancement Without Paired Supervision

@article{Jiang2021EnlightenGANDL,
  title={EnlightenGAN: Deep Light Enhancement Without Paired Supervision},
  author={Yi-fan Jiang and Xinyu Gong and Ding Liu and Yu Han Cheng and Chen Fang and Xiaohui Shen and Jianchao Yang and Pan Zhou and Zhangyang Wang},
  journal={IEEE Transactions on Image Processing},
  year={2021},
  volume={30},
  pages={2340-2349}
}
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. [...] Key Method 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…Expand
Enhance Image as You Like with Unpaired Learning
TLDR
A lightweight one-path conditional generative adversarial network (cGAN) is proposed to learn a one-to-many relation from low-light to normal-light image space, given only sets of low- and normal- light training images without any correspondence.
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement
TLDR
A deep recursive band network (DRBN) is proposed to recover a linear band representation of an enhanced normal-light image with paired low/normal-light images, and then obtain an improved one by recomposing the given bands via another learnable linear transformation based on a perceptual quality-driven adversarial learning with unpaired data.
A Two-Stage Unsupervised Approach for Low Light Image Enhancement
TLDR
This paper proposes a two-stage unsupervised method that decomposes the low light image enhancement into a pre-enhancement and a post-refinement problem and shows that the method can significantly improve feature points matching and simultaneous localization and mapping in low light conditions.
RetinexGAN:Unsupervised Low-Light Enhancement With Two-Layer Convolutional Decomposition Networks
TLDR
Both quantitative and visual results show that RetinexGAN is largely superior to state-of-the-art methods.
Invertible Network for Unpaired Low-light Image Enhancement
  • Jize Zhang, Haolin Wang, Xiaohe Wu, W. Zuo
  • Computer Science, Engineering
    ArXiv
  • 2021
TLDR
This work proposes to leverage the invertible network to enhance low-light image in forward process and degrade the normal-light one inversely with unpaired learning, and designs various loss functions to ensure the stability of training and preserve more image details.
Low-Light Image Enhancement Based on Generative Adversarial Network
Image enhancement is considered to be one of the complex tasks in image processing. When the images are captured under dim light, the quality of the images degrades due to low visibility degenerating
LEUGAN: Low-Light Image Enhancement by Unsupervised Generative Attentional Networks
TLDR
An unsupervised generation network with attention-guidance to handle the lowlight image enhancement task, which contains an edge auxiliary module that restores sharper edges and an attention guidance module that recovers more realistic colors.
DB-GAN: Boosting Object Recognition Under Strong Lighting Conditions
TLDR
A novel approach for tackling brightness variation in the domain of 2D object detection and 6D object pose estimation by proposing the usage of Generative Adversarial Networks in order to learn how to normalise the illumination of an input image.
R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network
TLDR
This paper proposes a novel Real-low to Real-normal Network for low-light image enhancement, dubbed R2RNet, based on the Retinex theory, which includes three subnets: a Decom-Net, a Denoise- net, and a Relight-Net that can properly improve the contrast and suppress noise simultaneously.
ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement
TLDR
A novel deep reinforcement learning based method, dubbed ReLLIE, for customized low-light enhancement, which models LLIE as a markov decision process, i.e., estimating the pixel-wise image-specific curves sequentially and recurrently.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 68 REFERENCES
Single Image Dehazing via Conditional Generative Adversarial Network
TLDR
This paper proposes an algorithm to directly restore a clear image from a hazy image based on a conditional generative adversarial network (cGAN), where the clear image is estimated by an end-to-end trainable neural network.
Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs
TLDR
An unpaired learning method for image enhancement based on the framework of two-way generative adversarial networks (GANs) with several improvements that significantly improve the stability of GAN training for this application.
LLNet: A deep autoencoder approach to natural low-light image enhancement
TLDR
It is shown that a variant of the stacked-sparse denoising autoencoder can learn from synthetically darkened and noise-added training examples to adaptively enhance images taken from natural low-light environment and/or are hardware-degraded.
Unsupervised Class-Specific Deblurring
TLDR
An end-to-end deblurring network designed specifically for a class of data that learns a strong prior on the clean image domain using adversarial loss and maps the blurred image to its clean equivalent and imposes a scale-space gradient error with an additional gradient module.
Unsupervised Single Image Deraining with Self-Supervised Constraints
TLDR
An Unsupervised Deraining Generative Adversarial Network (UD-GAN) is proposed to tackle single image deraining problems by introducing self-supervised constraints from the intrinsic statistics of unpaired rainy and clean images.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, Lucas Theis, +6 authors W. Shi
  • Computer Science, Mathematics
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.
Deep Retinex Decomposition for Low-Light Enhancement
TLDR
Extensive experiments demonstrate that the proposed deep Retinex-Net learned on this LOw-Light dataset not only achieves visually pleasing quality for low-light enhancement but also provides a good representation of image decomposition.
Towards Perceptual Image Dehazing by Physics-Based Disentanglement and Adversarial Training
TLDR
This work proposes Disentangled Dehazing Network, an end-to-end model that generates realistic haze-free images using only unpaired supervision by introducing a physical-model based disentanglement and reconstruction mechanism.
Unsupervised Image Super-Resolution Using Cycle-in-Cycle Generative Adversarial Networks
TLDR
This work proposes a Cycle-in-Cycle network structure with generative adversarial networks (GAN) as the basic component to tackle the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable.
Learning to See in the Dark
TLDR
A pipeline for processing low-light images is developed, based on end-to-end training of a fully-convolutional network that operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data.
...
1
2
3
4
5
...