Towards Unsupervised Deep Image Enhancement With Generative Adversarial Network

@article{Ni2020TowardsUD,
  title={Towards Unsupervised Deep Image Enhancement With Generative Adversarial Network},
  author={Zhangkai Ni and Wenhan Yang and Shiqi Wang and Lin Ma and Sam Tak Wu Kwong},
  journal={IEEE Transactions on Image Processing},
  year={2020},
  volume={29},
  pages={9140-9151}
}
Improving the aesthetic quality of images is challenging and eager for the public. To address this problem, most existing algorithms are based on <italic>supervised</italic> learning methods to learn an automatic photo enhancer for <italic>paired</italic> data, which consists of low-quality photos and corresponding expert-retouched versions. However, the style and characteristics of photos retouched by experts may not meet the needs or preferences of general users. In this paper, we present an… 
Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement
TLDR
A novel Cycle-Interactive Generative Adversarial Network for unsupervised low-light image enhancement, capable of not only better transferring illumination distributions between low/normal-light images but also manipulating detailed signals between two domains, e.g. suppressing/synthesizing realistic noise in the cyclic enhancement/degradation process is proposed.
Lighting the Darkness in the Deep Learning Era
TLDR
A comprehensive survey to cover various aspects ranging from algorithm taxonomy to unsolved open issues and a unified online platform that covers many popular LLIE methods, of which the results can be produced through a user-friendly web interface is provided.
Generalized Visual Quality Assessment of GAN-Generated Face Images
TLDR
This work develops a quality assessment model that is able to deliver accurate quality predictions for GFIs from both available and unseen GAN algorithms based on meta-learning, and develops the convolutional block attention and facial attributes-based analysis modules, ensuring that the learned knowledge tends to be consistent with human visual perception.
Low-Light Image and Video Enhancement Using Deep Learning: A Survey.
TLDR
This paper proposes a low-light image and video dataset, in which the images and videos are taken by different mobile phones' cameras under diverse illumination conditions, and provides a unified online platform that covers many popular LLIE methods.
Diverse and Adjustable Versatile Image Enhancer
TLDR
This work proposes a novel framework, Diverse and adjustable Versatile Image Enhancer (DaVIE), that learns from multiple ER images simultaneously and can output diverse results without being bound to a specific enhancement style while allowing users to freely adjust the level of enhancement.
An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement
TLDR
This work proposes an efficient adversarial video enhancement framework that learns directly from unpaired video examples and introduces new recurrent cells that consist of interleaved local and global modules for implicit integration of spatial and temporal information.
Joint Depth and Density Guided Single Image De-Raining
Single image de-raining is an important and highly challenging problem. To address this problem, some depth or density guided single-image de-raining methods have been developed with encouraging
Deep Video Coding with Dual-Path Generative Adversarial Network
TLDR
This paper proposes a dual-path enhancement with generative adversarial network (DPEG) to reconstruct the compressed video details and employs a joint training of deep video compression and enhancement to further improve the rate-distortion (RD) performance.
Learning-Based Video Coding with Joint Deep Compression and Enhancement
TLDR
This paper proposes an efficient end-to-end deep video codec with jointly optimized compression and enhancement modules (JCEVC), and proposes a dual-path generative adversarial network (DPEG) to reconstruct video details after compression.
Exposure Correction Model to Enhance Image Quality
TLDR
It is shown that after applying exposure correction with the proposed model, the portrait matting quality increases significantly and the state-of-the-art result on a large-scale exposure dataset is achieved.
...
...

References

SHOWING 1-10 OF 38 REFERENCES
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.
NIMA: Neural Image Assessment
TLDR
The proposed approach relies on the success (and retraining) of proven, state-of-the-art deep object recognition networks and can be used to not only score images reliably and with high correlation to human perception, but also to assist with adaptation and optimization of photo editing/enhancement algorithms in a photographic pipeline.
Underexposed Photo Enhancement Using Deep Illumination Estimation
TLDR
A new neural network for enhancing underexposed photos is presented, which introduces intermediate illumination in its network to associate the input with expected enhancement result, which augments the network's capability to learn complex photographic adjustment from expert-retouched input/output image pairs.
Self-Attention Generative Adversarial Networks
TLDR
The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset.
Automatic Photo Adjustment Using Deep Neural Networks
TLDR
This article forms automatic photo adjustment in a manner suitable for deep neural networks, and introduces an image descriptor accounting for the local semantics of an image that can model local adjustments that depend on image semantics.
Deep bilateral learning for real-time image enhancement
TLDR
This work introduces a new neural network architecture inspired by bilateral grid processing and local affine color transforms that processes high-resolution images on a smartphone in milliseconds, provides a real-time viewfinder at 1080p resolution, and matches the quality of state-of theart approximation techniques on a large class of image operators.
LIME: Low-Light Image Enhancement via Illumination Map Estimation
TLDR
Experiments on a number of challenging low-light images are present to reveal the efficacy of the proposed LIME and show its superiority over several state-of-the-arts in terms of enhancement quality and efficiency.
COCO-GAN: Generation by Parts via Conditional Coordinating
TLDR
COnditional COordinate GAN (COCO-GAN) of which the generator generates images by parts based on their spatial coordinates as the condition and the discriminator learns to justify realism across multiple assembled patches by global coherence, local appearance, and edge-crossing continuity is proposed.
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
...
...