Fast efficient algorithm for enhancement of low lighting video

By Xuan Dong, Yi Pang, Jiangtao Wen. IEEE International Conference on Multimedia and Expo, 2010

639 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/900d8546e441094acbc09e90cb4c27e106e5cac9

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 Signal Processing

Citations in the corpus

Benchmarking Low-Light Image Enhancement and Beyond (2021, methodology): “We test state-of-the-art algorithms for light/contrast enhancement: Multi-Scale Retinex (MSR) (Jobson et al. 1997a), Inverse Dehazing (Dehazing) (Dong et al. 2011), Bright-ness Preserving Dynamic Histogram Equalization (BPDHE) (Ibrahim and Pik Kong 2007), Naturalness Preserved Enhancement (NPE)…”
Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method (2022, methodology): “Traditional LLIE methods are mainly based on image priors or physical models from other tasks, such as histogram equalization-based meth-ods (Kim 1997; Stark 2000), retinex-based methods (Kimmel et al. 2003; Wang et al. 2014) and dehazing-based meth-ods (Dong et al. 2011; Zhang et al. 2012).”
SNR-Aware Low-light Image Enhancement (2022, methodology): “Methods Dong [9] LIME [15] MF [11] SRIE [12] BIMEF [55] DRD [45] RRM [28] SID [5] DeepUPE [40] KIND [61] DeepLPF [33] FIDE [48] PSNR 17.”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, positive): “The haze image is generated from the model : 3) Effect of Dehazing: We further evaluate the current state-of-the-art dehazing approaches on hazy dataset, with pre-trained detectors subsequently applied without tuning or adaptation.”
Beyond Brightening Low-light Images (2021, methodology): “The methods like Dong and Retinex-Net obtain poor values and rankings because their results contain obvious over-smoothing, unnat-ural texture, and/or hue shift issues.”
MBLLEN: Low-Light Image/Video Enhancement Using CNNs (2018, methodology): “Using such low quality images due to low light will certainly reduce the performance of most vision-based algorithms, and thus, (a) Input (b) Dong [9] (c) NPE [37] (d) LIME [14] (e) Ying [43] (f) BIMEF [41] (g) Ours (MBLLEN) (h) Ground Truth it is highly demanded by real applications to enhance the…”
Low-Light Image Enhancement With Semi-Decoupled Decomposition (2020, methodology): “In this perspective, our decomposition model lies between the coupled models [1]–[4], [6] and the decoupled models [7], [8] that only estimates I .”
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (2020, background): “Metric BIMEF [31] BPDHE [10] CRM [33] DHECE [22] Dong [6] EFF [32] CLAHE [36] LIME [9] MF [7]”
Low-Light Image Enhancement via a Deep Hybrid Network (2019, background): “Retinex theory [34] assumes that the amount of light reaching observers can be decomposed into illumination and scene reflection [35]–[37].”
LIME: Low-Light Image Enhancement via Illumination Map Estimation (2017, background): “As noticed in [14], inverted lowlight images look like haze images, as shown in Fig.”
MSR-net: Low-light Image Enhancement Using Deep Convolutional Network (2017, methodology): “Inspired by the dark channel method on de-hazing, [8] ﬁnds the inverted low-light image looks like haze image.”
Learning Enriched Features for Real Image Restoration and Enhancement (2020, methodology): “Method BIMEF CRM Dong LIME MF RRM SRIE Retinex-Net MSR NPE GLAD KinD MIRNet [115] [116] [28] [39] [33] [66] [33] [106] [52] [100] [101] [122] (Ours)”
Deep Retinex Decomposition for Low-Light Enhancement (2018, methodology): “We compare our Retinex-Net with four state-of-the-art methods, including de-hazing based method (DeHz) [5], naturalness preserved enhancement algorithm (NPE) [23], simultaneous reflectance and illumination estimation algorithm (SRIE) [8], and illumination map estimation based (LIME) [9].”
An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, methodology): “…image, and panels (b)-(r) display the results of many enhancement methods: Gamma correction [3], AHE [78], WT [166], BIMEF [223], CegaHE [102], CRM [225], CVC [89], Dong et al. [229], MBLLEN [263], HMF [101], LIME [13], MF [219], HE [66], MSRCP [127], MSRCR [115], NPE [136], and SRIE [126].”
GLADNet: Low-Light Enhancement Network with Global Awareness (2018, methodology): “De-hazing based methods [6] utilize the high similarity between low-light images and those with the dense fog.”
Kindling the Darkness: A Practical Low-light Image Enhancer (2019, methodology): “Metrics BIMEF [32] CRM [33] Dong [34] LIME [11] MF [35] RRM [13] PSNR 13.”