A Variational Framework for Retinex

By Ron Kimmel, Michael Elad, D. Shaked, R. Keshet, I. Sobel. IS&T/SPIE Electronic Imaging, 2002

713 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2575a8aab02920c29dabf2aa1235dc7b3e29c5b0

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 Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation (2015, methodology): “Since the reflectance is sometimes overenhanced [29], [30], [37], a Gamma correction operation is adopted for post-processing, similar to previous studies [29], [30], [37].”
An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, background): “Kimmel et al. used the transcendental hypothesis to propose a Retinex algorithm based on a variational framework [120], in which the problem of illumination estimation is transformed into an optimal quadratic programming problem.”
LR3M: Robust Low-Light Enhancement via Low-Rank Regularized Retinex Model (2020, methodology): “In [12]–[14], variational models are used to estimate the smooth illumination layer and piecewise continuous reﬂectance layer of the Retinex model.”
A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation (2016, background): “In [11], Kimmel et al. propose a variational model to estimate the illumination, which is assumed varies smoothly .”
High dynamic range image rendering with a retinex-based adaptive filter (2006, background): “developed their quadratic programming optimization algorithm for a monochrome image [22], [23].”
STAR: A Structure and Texture Aware Retinex Model (2019, methodology): “With this property, the Retinex decomposition can be performed by classifying the image gradients into the reflectance component and the illumination one [9].”
URetinex-Net: Retinex-based Deep Unfolding Network for Low-light Image Enhancement (2022, background): “Several Retinex decomposition models [9, 18, 27] have been proposed under variational frameworks.”
Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method (2022, methodology): “Traditional methods mainly include histogram-based methods (Lee, Lee, and Kim 2012; Xu et al. 2013; Celik 2014), Retinex-based methods (Kimmel et al. 2003; Wang et al. 2014), and dehazing-based meth-ods (Zhang et al. 2012; Li et al. 2015).”
Multiscale Retinex (2014, methodology): “The second group uses a convolution mask or variational techniques to compute a local contrast result [11, 8, 7, 9, 1, 18, 15, 2].”
A fusion-based enhancing method for weakly illuminated images (2016, methodology): “However, for some illumination-estimating algorithms based on Retinex theory, parameters are not easily designed [17,18], while other methods”
Total variation models for variable lighting face recognition (2006, methodology): “squares within a variational framework by Brajovic [7, 8]. Kimmel et al. [ 21 ] and Elad et al.”