Color Constancy by GANs: An Experimental Survey

Das, Partha Pratim; Baslamisli, Anil S.; Liu, Yang; Karaoğlu, Sezer; Gevers, Theo

doi:10.48550/arxiv.1812.03085

Cited by 7 publications

(9 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its main function is to ensure that the color perceived by vision maintains a relatively constant value under changing lighting conditions. The main methods to solve the problem of color constancy are partitioned into two Kinds: Statistics-based methods [28][29][30][31][32] and learning-based methods [12,13,[33][34][35][36]. Statistical-based methods generally do not rely on the prior knowledge of the sample, and directly use the image information of the sample to estimate the illumination during image imaging.…”

Section: Color Constancymentioning

confidence: 99%

Illumination correction via improved grey wolf optimizer for regularized random vector functional link network

2023

KSII TIIS

View full text Add to dashboard Cite

In a random vector functional link (RVFL) network, shortcomings such as local optimal stagnation and decreased convergence performance cause a reduction in the accuracy of illumination correction by only inputting the weights and biases of hidden neurons. In this study, we proposed an improved regularized random vector functional link (RRVFL) network algorithm with an optimized grey wolf optimizer (GWO). Herein, we first proposed the moth-flame optimization (MFO) algorithm to provide a set of excellent initial populations to improve the convergence rate of GWO. Thereafter, the MFO-GWO algorithm simultaneously optimized the input feature, input weight, hidden node and bias of RRVFL, thereby avoiding local optimal stagnation. Finally, the MFO-GWO-RRVFL algorithm was applied to ameliorate the performance of illumination correction of various test images. The experimental results revealed that the MFO-GWO-RRVFL algorithm was stable, compatible, and exhibited a fast convergence rate.

show abstract

Section: Color Constancymentioning

confidence: 99%

Illumination correction via improved grey wolf optimizer for regularized random vector functional link network

2023

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…The Bayesian approach estimates the illumination colour and reflectance of materials from the posterior distribution of colour intensities [21]. Other learning-based methods for achieving CC include those using k-nearest neighbor [22], convolutional neural networks (CNN) [23], [24], [25], [26], generative adversarial networks (GANs) [27], convolutional autoencoder (CAE) [28], [29], [30], etc.…”

Section: Related Work a White Balancementioning

confidence: 99%

Color Alignment for Relative Color Constancy via Non-Standard References

Zhao

Ferguson

Zhou

et al. 2022

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Relative colour constancy is an essential requirement for many scientific imaging applications. However, most digital cameras differ in their image formations and native sensor output is usually inaccessible, e.g., in smartphone camera applications. This makes it hard to achieve consistent colour assessment across a range of devices, and that undermines the performance of computer vision algorithms. To resolve this issue, we propose a colour alignment model that considers the camera image formation as a black-box and formulates colour alignment as a threestep process: camera response calibration, response linearisation, and colour matching. The proposed model works with nonstandard colour references, i.e., colour patches without knowing the true colour values, by utilising a novel balance-of-lineardistances feature. It is equivalent to determining the camera parameters through an unsupervised process. It also works with a minimum number of corresponding colour patches across the images to be colour aligned to deliver the applicable processing. Three challenging image datasets collected by multiple cameras under various illumination and exposure conditions, including one that imitates uncommon scenes such as scientific imaging, were used to evaluate the model. Performance benchmarks demonstrated that our model achieved superior performance compared to other popular and state-of-the-art methods.

show abstract

“…More recent approaches try to exploit the power of different deep learning architectures, such as for example Generative Adversarial Networks (GANs) [17,15], or use different modules, such as for example Attention [29,40].…”

Section: Exploiting Deep Learningmentioning

confidence: 99%

Image understanding for color constancy and vice versa

Bianco¹,

Buzzelli²

2021

lim

View full text Add to dashboard Cite

In this article we show the change in paradigm occurred in color constancy algorithms: from a pre-processing step in image understanding, to the exploitation of image understanding and computer vision results and techniques. Since color constancy is an ill-posed problem, we give an overview of the assumptions on which classical color constancy algorithms are based in order to solve it. Then, we chronologically review the color constancy algorithms that exploit results and techniques borrowed from the image understanding research field in order to exploit assumptions that could be met in a larger number of images.

show abstract

Color Constancy by GANs: An Experimental Survey

Cited by 7 publications

References 39 publications

Illumination correction via improved grey wolf optimizer for regularized random vector functional link network

Illumination correction via improved grey wolf optimizer for regularized random vector functional link network

Color Alignment for Relative Color Constancy via Non-Standard References

Image understanding for color constancy and vice versa

Contact Info

Product

Resources

About