Low-light Image Enhancement

We proposed a deep network for low-light image enhancement

From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement

Weibo

Cited by3BibtexViews146Links

Wenhan Yang,Shiqi Wang, Yuming Fang, Yue Wang,Jiaying Liu

CVPR, pp.3060-3069, (2020)

We aim to create a novel semi-supervised learning method utilizing the knowledge of synthetic paired low/normal-light images and unpaired high-quality data for low-light image enhancement

Learning to Restore Low-Light Images via Decomposition-and-Enhancement

Weibo

Cited by1BibtexViews131Links

Ke Xu,Xin Yang,Baocai Yin,Rynson W.H. Lau

CVPR, pp.2278-2287, (2020)

We have presented a network with the proposed Attention to Context Encoding module for adaptively enhancing the high and low frequency layers, and Cross Domain Transformation module for noise suppression and detail enhancement

A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising

Weibo

Cited by0BibtexViews65Links

Wei Kaixuan,Fu Ying,Yang Jiaolong,Huang Hua

CVPR, pp.2755-2764, (2020)

We have presented a physics-based noise formation model together with a noise parameter calibration method to help resolve the difficulty of extreme low-light denoising

GIA-Net: Global Information Aware Network for Low-light Imaging

Weibo

Cited by0BibtexViews82Links

Zibo Meng, Runsheng Xu, Chiu Man Ho

It is extremely challenging to acquire perceptually plausible images under low-light conditions due to low SNR. Most recently, U-Nets have shown promising results for low-light imaging. However, vanilla U-Nets generate images with artifacts such as color inconsistency due to th...

DALE : Dark Region-Aware Low-light Image Enhancement

Weibo

Cited by0BibtexViews13Links

Dokyeong Kwon, Guisik Kim,Junseok Kwon

BMVC, (2020)

Experimental results demonstrate that our method outperforms state-of-the-art methods

Deep Bilateral Retinex for Low-Light Image Enhancement

Weibo

Cited by0BibtexViews69Links

Jinxiu Liang, Yong Xu,Yuhui Quan, Jingwen Wang,Haibin Ling,Hui Ji

Motivated by the inherently coupled relationship between illumination and measurement noise, we proposed a novel deep bilateral Retinex method, which performs Retinex decomposition in the bilateral space of lowlight images

Attention-based network for low-light image enhancement

Weibo

Cited by0BibtexViews47Links

Zhang Cheng,Yan Qingsen, zhu Yu, Li Xianjun,Sun Jinqiu,Zhang Yanning

ICME, pp.1-6, (2020)

We propose a novel Attention-based Low-light image Enhancement Network which directly converts raw image to color image

Extreme Low-Light Imaging with Multi-granulation Cooperative Networks

Weibo

Cited by0BibtexViews89Links

Wang Keqi,Gao Peng,Hoi Steven, Guo Qian, Qian Yuhua

A novel network architecture has been proposed for processing extreme low-light images and correspondingly the loss function has been modified for our task and the raw illumination map estimation function is designed to preserve high dynamic range in low-light environment

Visual Perception Model for Rapid and Adaptive Low-light Image Enhancement

Weibo

Cited by0BibtexViews84Links

Li Xiaoxiao, Guo Xiaopeng, Mei Liye, Shang Mingyu, Gao Jie, Shu Maojing, Wang Xiang

We proposed the VP model to simulate the relationship between light source and H UMAN vision system, aiming at quantifying the visual perception information of images

Unsupervised Real-world Low-light Image Enhancement with Decoupled Networks

Weibo

Cited by0BibtexViews28Links

Wei Xiong,Ding Liu,Xiaohui Shen, Chen Fang,Jiebo Luo

arxiv, (2020)

We conduct experiments on three real-world datasets and show that our model outperforms the state-of-the-art models with respect to both contrast enhancement and image denoising

Learning an Adaptive Model for Extreme Low-light Raw Image Processing

Weibo

Cited by0BibtexViews99Links

Fu Qingxu, Di Xiaoguang, Zhang Yu

IET Image Process., no. 14 (2020): 3433-3443

Our model has the smallest noise variance on the Noise Level Estimation metric compared to BM3D-based low-light methods and obtains near-optimal scores on the other three indices

Burst Denoising of Dark Images

Weibo

Cited by0BibtexViews28Links

Karadeniz Ahmet Serdar,Erdem Erkut, Erdem Aykut

We propose a coarse-to-fine network architecture which allows for simultaneous processing of a burst of raw dark images as input to obtain a high quality RGB image

Self-supervised Image Enhancement Network: Training with Low Light Images Only

Weibo

Cited by0BibtexViews41Links

Zhang Yu, Di Xiaoguang,Zhang Bin, Wang Chunhui

We propose a maximum entropy based Retinex model and a self-supervised image enhancement network

Underexposed Photo Enhancement Using Deep Illumination Estimation

Weibo

Cited by0BibtexViews30Links

Ruixing Wang,Qing Zhang,Chi-Wing Fu,Xiaoyong Shen,Wei-Shi Zheng,Jiaya Jia

CVPR, pp.6849-6857, (2019)

This paper presents a new neural network for enhancing underexposed photos

Low-Light Image Enhancement via a Deep Hybrid Network

Weibo

Cited by62BibtexViews61Links

Wenqi Ren,Sifei Liu,Lin Ma,Qianqian Xu,Xiangyu Xu,Xiaochun Cao,Junping Du,Ming-Hsuan Yang

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, pp.1-1, (2019)

Camera sensors often fail to capture clear images or videos in a poorly-lit environment. In this paper, we propose a trainable hybrid network to enhance the visibility of such degraded images. The proposed network consists of two distinct streams to simultaneously learn the globa...

EnlightenGAN: Deep Light Enhancement without Paired Supervision

Weibo

Cited by32BibtexViews96Links

Yifan Jiang,Xinyu Gong,Ding Liu,Yu Cheng,Chen Fang,Xiaohui Shen,Jianchao Yang, Pan Zhou,Zhangyang Wang

CoRR, (2019)

We address the low-light enhancement problem with a novel and flexible unsupervised framework

Kindling the Darkness: A Practical Low-light Image Enhancer

Weibo

Cited by15BibtexViews132Links

Yonghua Zhang,Jiawan Zhang,Xiaojie Guo

Proceedings of the 27th ACM International Conference on Multimedia, (2019): 1632-1640

Images captured under low-light conditions often suffer from (partially) poor visibility. Besides unsatisfactory lightings, multiple types of degradations, such as noise and color distortion due to the limited quality of cameras, hide in the dark. In other words, solely turning u...

Low-light image enhancement using Gaussian Process for features retrieval

Weibo

Cited by11BibtexViews43Links

Yuen Peng Loh,Xuefeng Liang,Chee Seng Chan

Sig. Proc.: Image Comm., (2019): 175-190

We modeled low-light image enhancement as a distribution of localized enhancement functions using Gaussian Process trained at runtime with reference data generated from a CNN

Attention Guided Low light Image Enhancement with a Large Scale Low light Simulation Dataset

Weibo

Cited by8BibtexViews66Links

Feifan Lv, Yu Li, Feng Lu

arXiv preprint arXiv:1908.00682, (2019)

Extensive experiments demonstrate that our solution outperforms state-of-the-art methods by a large margin