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… 
[PDF] Semantic Reader
24 Citations
Highly Influential Citations
4
Background Citations
13
Methods Citations
11

24 Citations

Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement

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.

Contextual Information Aided Generative Adversarial Network for Low-Light Image Enhancement

Qualitative and quantitative experimental results demonstrate that the proposed improved generative adversarial network achieves relatively good results and has good generalization capacity compared to other state-of-the-art low-light enhancement algorithms.

Lighting the Darkness in the Deep Learning Era

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

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.

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

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

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

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

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.

References

SHOWING 1-10 OF 38 REFERENCES

Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs

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.

EnlightenGAN: Deep Light Enhancement Without Paired Supervision

This paper proposes 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.

DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks

An end-to-end deep learning approach that bridges the gap by translating ordinary photos into DSLR-quality images by learning the translation function using a residual convolutional neural network that improves both color rendition and image sharpness.

Underexposed Photo Enhancement Using Deep Illumination Estimation

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.

Exposure: A White-Box Photo Post-Processing Framework

This paper presents a deep learning approach that is instead trained on unpaired data, namely a set of photographs that exhibits a retouching style the user likes, which is much easier to collect.

Self-Attention Generative Adversarial Networks

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

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

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.

Low-Light Image Enhancement via a Deep Hybrid Network

A novel spatially variant recurrent neural network (RNN) is proposed as an edge stream to model edge details, with the guidance of another auto-encoder, to enhance the visibility of degraded images.

LIME: Low-Light Image Enhancement via Illumination Map Estimation

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.