Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images

By Jianrui Cai, Shuhang Gu, Lei Zhang. IEEE Transactions on Image Processing, 2018

1,144 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/d5e3381d381a4cd564c9efb0d3cfdaec7ab18490

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, methodology): “Inspired by the multiple image fusion method, Cai et al. [273] proposed a framework based on a CNN trained to enhance single images.”
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (2020, methodology): “…Enhancement and Denoising Method (JED) [25], Reﬁned Retinex Model (RRM) [18], Simultaneous Reﬂectance and Illumination Estimation (SRIE) [8], Deep Retinex Decomposition (DRD) [30], Deep Underexposed Photo Enhancement (DeepUPE) [27], Single Image Contrast Enhancer (SICE) [2], EnlightenGAN [11].”
Low-Light Image Enhancement with Normalizing Flow (2021, methodology): “…DeepUPE (Wang et al. 2019a) 13.19 0.4902 0.4634 JED (Ren et al. 2018) 16.73 0.6817 0.3899 LIME (Guo, Li, and Ling 2016) 14.07 0.5274 0.4021 SICE (Cai, Gu, and Zhang 2018) 18.06 0.7094 0.5078 LLNet (Lore et al. 2017) 17.57 0.7388 0.4021 SRIE (Fu et al. 2016) 13.66 0.5509 0.4577 KinD (Zhang et…”
Low-Light Image Enhancement With Semi-Decoupled Decomposition (2020, methodology): “In recent years, Convolutional Neural Network (CNN) has been broadly applied [20]–[22], where skip connection is used to preserve image details.”
Rethinking the Image Fusion: A Fast Unified Image Fusion Network based on Proportional Maintenance of Gradient and Intensity (2020, methodology): “2 https://drive.google.com/drive/folders/ 0BzXT0LnoyRqlVjhtOEhiUzU5a2M the dataset provided by (Cai, Gu, and Zhang 2018) for task2; MRI and PET images from Harvard medical school web-site 3 for task3; the dataset provided by (Nejati, Samavi, and Shirani 2015) and sametaymaz 4 for task4; and the…”
Underexposed Photo Enhancement Using Deep Illumination Estimation (2019, background): “[5] learned a contrast enhancer from multi-exposure images.”
EnlightenGAN: Deep Light Enhancement Without Paired Supervision (2019, methodology): “aired training set, that covers diverse image qualities and contents. We assemble a mixture of 914 low light and 1016 normal light images from several datasets released in [43,5] and also HDR sources [15,25], without the need to keep any pair.1 Manual inspection and selection are performed to remove”
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation (2021, methodology): “To this end, we employ 360 multi-exposure sequences from the Part1 of SICE dataset [38] to train our”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, methodology): “[110] built a dataset of under/over-contrast and normal-contrast encoded image pairs, in which the reference normal-contrast images are generated by Multi-Exposure image Fusion or High Dynamic”
URetinex-Net: Retinex-based Deep Unfolding Network for Low-light Image Enhancement (2022, methodology): “For a more convincing comparison, we extend our model to SICE dataset [2], which contains 589 natural scenes with multi-level exposure, and randomly select 108 under/normal exposure image pairs from it.”
Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset (2019, methodology): “[77] [73] [8]”
Beyond Brightening Low-light Images (2021, methodology): “The testing data includes 93 low-light images from the LOL, DICM, LIME, NPE, and MEF datasets, and extra 50 low-light images from a public dataset, i.e. SICE dataset (Cai et al. 2018).”
Learning a Simple Low-Light Image Enhancer from Paired Low-Light Instances (2023, methodology): “We collect low-light image pairs from SICE (part2) [2] and LOL (training set) [32], which contain multi-exposure images.”
Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method (2022, background): “(Cai, Gu, and Zhang 2018) synthesized the SICE dataset from 589 image sequences with multi-exposure image fusion (MEF) or a high dynamic range (HDR) algo-rithm.”
Learning Image-Adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-Time (2020, background): “For the enhancement part, those modules include exposure correction [13], [14], color constancy [15], [16], contrast enhancement [17], [18], color manipulation [19], [20] and tone mapping [21], [22], each of which has been widely studied in the past.”
U2Fusion: A Unified Unsupervised Image Fusion Network (2020, methodology): “dataset in [41] EMPA the best result on CC and the optimal result on VIF show that U2Fusion maintains the highest linear correlation with source images and achieves comparable information ﬁdelity.”
Infrared and Visible Image Fusion with ResNet and zero-phase component analysis (2018, background): “Furthermore, in image reconstruction tasks[21]-[23], the performance gets better by use of the residual block.”