Unsupervised learning for color constancy

N Banić, K Koščević, S Lončarić - arXiv preprint arXiv:1712.00436, 2017 - arxiv.org
Most digital camera pipelines use color constancy methods to reduce the influence of
illumination and camera sensor on the colors of scene objects. The highest accuracy of color …

The cube++ illumination estimation dataset

E Ershov, A Savchik, I Semenkov, N Banić… - IEEE …, 2020 - ieeexplore.ieee.org
Computational color constancy has the important task of reducing the influence of the scene
illumination on the object colors. As such, it is an essential part of the image processing …

Deep learning-based illumination estimation using light source classification

K Koščević, M Subašić, S Lončarić - IEEE access, 2020 - ieeexplore.ieee.org
Color constancy is one of the key steps in the process of image formation in digital cameras.
Its goal is to process the image so that there is no influence of illumination color on the …

Deep learning-based computational color constancy with convoluted mixture of deep experts (CMoDE) fusion technique

HH Choi, BJ Yun - IEEE Access, 2020 - ieeexplore.ieee.org
In the human and computer vision, color constancy is the ability to perceive the true color of
objects in spite of changing illumination conditions. Color constancy is remarkably …

Color constancy based on local reflectance differences

M Yan, Y Hu, H Zhang - Electronics, 2023 - mdpi.com
Color constancy is used to determine the actual surface color of the scene affected by
illumination so that the captured image is more in line with the characteristics of human …

Color constancy algorithm for mixed-illuminant scene images

MA Hussain, AS Akbari - IEEE Access, 2018 - ieeexplore.ieee.org
The intrinsic properties of the ambient illuminant significantly alter the true colors of objects
within an image. Most existing color constancy algorithms assume a uniformly lit scene …

Iterative convolutional neural network-based illumination estimation

K Koščević, M Subašić, S Lončarić - IEEE access, 2021 - ieeexplore.ieee.org
In the image processing pipelines of digital cameras, one of the first steps is to achieve
invariance in terms of scene illumination, namely computational color constancy. Usually …

[PDF][PDF] Color beaver: Bounding illumination estimations for higher accuracy

K Košcevic, N Banic, S Loncaric - Proc. 14th Int. Joint …, 2019 - pdfs.semanticscholar.org
The image processing pipeline of most contemporary digital cameras performs illumination
estimation in order to remove the influence of illumination on image scene colors. In this …

[PDF][PDF] Color Dog-Guiding the Global Illumination Estimation to Better Accuracy.

N Banic, S Loncaric - VISAPP (1), 2015 - researchgate.net
An important part of image enhancement is color constancy, which aims to make image
colors invariant to illumination. In this paper the Color Dog (CD), a new learning-based …

A benchmark for burst color constancy

Y Qian, J Käpylä, JK Kämäräinen, S Koskinen… - Computer Vision–ECCV …, 2020 - Springer
Abstract Burst Color Constancy (CC) is a recently proposed approach that challenges the
conventional single-frame color constancy. The conventional approach is to use a single …