Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination Images

By Shuhang Wang, Jin Zheng, Hai-Miao Hu, Bo Li. IEEE Transactions on Image Processing, 2013

1,639 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e6887e7b20007c88aa0e9c48626f165d05eee273

How researchers see this paper

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

In Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

Citations in the corpus

MSR-net: Low-light Image Enhancement Using Deep Convolutional Network (2017, methodology): “On the other hand, in order to evaluate our approach objectively and impartially, we choose the real-world low-light images form the public MEF dataset [21, 33], NPE dataset [30] and VV dataset [27, 28].”
STAR: A Structure and Texture Aware Retinex Model (2019, methodology): “We compare the proposed STAR model with previous competing low-light image enhancement methods, including HE [47], MSRCR [19], Contextual and Variational Contrast (CVC) [48], Naturalness Preserved Enhancement (NPE) [5], LDR [49], SIRE [32], MF [50], WVM [7], LIME [6], and JieP [8].”
Learning Enriched Features for Real Image Restoration and Enhancement (2020, neutral): “aset [107]. The proposed method signicantly advances the state-of-the-art. Method BIMEF CRM Dong LIME MF RRM SRIE Retinex-Net MSR NPE GLAD KinD MIRNet [116] [117] [29] [40] [34] [67] [34] [107] [54] [101] [102] [124] (Ours) PSNR 13.86 17.20 16.72 16.76 18.79 13.88 11.86 16.77 13.17 16.97 19.72 20.87”
Structure-Revealing Low-Light Image Enhancement Via Robust Retinex Model (2018, methodology): “NPE is designed to preserve the naturalness of images, and most of its results have vivid color.”
EnlightenGAN: Deep Light Enhancement Without Paired Supervision (2019, methodology): “dex. EnlightenGAN produces the most top-ranking images and gains the best performance with the smallest average ranking value. our unpaired training set, RetinexNet [5], SRIE [20], LIME [21], and NPE [19]. The last column shows the results produced by EnlightenGAN. We next zoom in on some details in”
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (2020, background): “Variants of Retinex models, e.g. single-scale Retinex [14], multi-scale Retinex [12], naturalness Retinex [28], and robust Retinex [18, 25] are developed to facilitate low-light image enhancement.”
An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, methodology): “The NPE, SRIE and MELLEN methods have the lowest computational efﬁciency for processing a single image because of the use of iterative computations to ﬁnd the optimal solution.”
Underexposed Photo Enhancement Using Deep Illumination Estimation (2019, background): “Hence, photo enhancement can be formulated as an illumination estimation problem, where illumination is estimated to enhance the underexposed photos [27, 11, 31, 14, 4, 33].”
Kindling the Darkness: A Practical Low-light Image Enhancer (2019, methodology): “6096 NPE [9] 3.”
A retinex-based enhancing approach for single underwater image (2014, methodology): “Inspired by the Bi-log Transformation [16], the number of the gray intensity is utilized as a weight to generate a weighted histogram.”
Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs (2018, methodology): “Figure 4 compares our models with several methods including DPED [10] (Figure 4(f)), CLHE [21] (Figure 4(g)), NPEA [22] (Figure 4(h)) and FLLF [2] (Figure 4(i)).”
A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation (2015, methodology): “Many methods that decompose an image into the illumination and the reflectance have been used in a series of applications, such as contrast enhancement [2]–[4], non-uniform illumination images enhancement [5], tone mapping [6]–[10], remote sensing image correction [11], image segmentation [12] and t”
Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement (2021, methodology): “Several ﬁlters [4]–[6] are designed for that decomposition.”
A fusion-based enhancing method for weakly illuminated images (2016, methodology): “Wecomparetheproposedmethodwithsixotherimage enhancementmethods:twoRetinex-basedmethods,MSR[16] andNPEA[20],twohistogram-basedmethods,CVC[10]andLDR [1],andtwofiltering-basedmethods,GUM[23]andGOLW[22].”