A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation

By Xueyang Fu, Yinghao Liao, Delu Zeng, Yue Huang, Xiao-Ping Zhang, Xinghao Ding. IEEE Transactions on Image Processing, 2015

414 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/0cc1b472370d76a9e6bf79c6e67f370e768d90aa

How researchers see this paper

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

1. Wenhan Yang
2. Chunle Guo
3. Jiaying Liu
4. Chongyi Li
5. Ling Shao
6. Chen Change Loy
7. Mengyang Yu
8. Wencheng Wang

Citations in the corpus

• Low-Light Image and Video Enhancement Using Deep Learning: A Survey (2021, methodology): “Traditional methods for low-light enhancement include Histogram Equalization-based methods [35], [36] and Retinex model-based methods [37], [38], [39], [40], [41], [42], [43], [44].”
• STAR: A Structure and Texture Aware Retinex Model (2019, methodology): “We first compare the performance of the proposed STAR with three leading Retinex methods: SIRE [32], WVM [7] and JieP [8].”
• Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior (2016, unknown): “…(SID) method [10], Dark Channel Prior (DCP) method [11], Chromatism-based (CB) underwater image dehazing method [17], Wavelength Compensation and Dehazing (WCID) underwater image enhancement method [18], Histogram Equalization (HE) method, and Probability-based (PB) image enhancement method [8].”
• An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, background): “Fu et al. [139] proposed a Retinex algorithm based on a variation framework that effectively enhances the contour details of an image while suppressing abnormal enhancement.”
• Toward Fast, Flexible, and Robust Low-Light Image Enhancement (2022, unknown): “Benefiting from the convenient solution of (cid:96) 2 -norm, Fu et al. [5, 6] firstly utilized the (cid:96) 2 -norm to constrain the illumination.”
• LR3M: Robust Low-Light Enhancement via Low-Rank Regularized Retinex Model (2020, methodology): “Some methods [15], [19], [38] use term ‖R · L−S‖F in their equations, and in order to calculate both R and L simultaneously, they iteratively update each variable while regarding the other variables as constants.”
• Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement (2020, unknown): “There are also various classical methods consider Retinex theory [26] and introduce different prior regularized optimization models to characterize the structures of the illumination and reflectance image layers [6, 9, 13, 46, 20].”
• Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors (2022, unknown): “Then, following works [3], [31], [32] that avoid potential color artifacts and reduce computational complexity, the color-corrected underwater image U is converted from RGB color space to HSV color space that is more robust to illumination variations.”
• Low-Light Image Enhancement With Semi-Decoupled Decomposition (2020, methodology): “Generally, the Retinex-based methods boil down to effectively solving the ill-posed I and R decomposition [1]–[3].”
• Structure-Revealing Low-Light Image Enhancement Via Robust Retinex Model (2018, methodology): “(a) is the input image; (b)–(f) are enhancement results of HE, LIME [13], NPE [11], PIE [23], and SRIE [14] with a post-processing performed by BM3D with the denoising parameter σ = 30; (g) is the result obtained by the proposed method with model (6).”