no code implementations • 31 Dec 2020 • Egor Ershov, Alex Savchik, Ilya Semenkov, Nikola Banić, Karlo Koscević, Marko Subašić, Alexander Belokopytov, Zhihao LI, Arseniy Terekhin, Daria Senshina, Artem Nikonorov, Yanlin Qian, Marco Buzzelli, Riccardo Riva, Simone Bianco, Raimondo Schettini, Sven Lončarić, Dmitry Nikolaev
The main advantage of testing a method on a challenge over testing in on some of the known datasets is the fact that the ground-truth illuminations for the challenge test images are unknown up until the results have been submitted, which prevents any potential hyperparameter tuning that may be biased.
1 code implementation • 21 Dec 2020 • Nikola Banić, Neven Elezović
Pearson's chi-squared test can detect outliers in the data distribution of a given set of histograms.
Methodology Discrete Mathematics
1 code implementation • 19 Nov 2020 • Egor Ershov, Alex Savchik, Illya Semenkov, Nikola Banić, Alexander Belokopytov, Daria Senshina, Karlo Koscević, Marko Subašić, Sven Lončarić
In this paper, a new illumination estimation dataset is proposed that aims to alleviate many of the mentioned problems and to help the illumination estimation research.
no code implementations • 29 Mar 2019 • Nikola Banić, Karlo Koščević, Marko Subašić, Sven Lončarić
For a given camera sensor it enables generation of any number of realistic raw images taken in a subset of the real world, namely images of printed photographs.
no code implementations • 11 Mar 2019 • Nikola Banić, Karlo Koš{č}ević, Marko Subašić, Sven Lon{č}arić
The pipelines of digital cameras contain a part for computational color constancy, which aims to remove the influence of the illumination on the scene colors.
no code implementations • 2 Feb 2018 • Nikola Banić, Sven Lončarić
In this paper it is first shown that the accuracy of statistics-based methods reported in most papers was not obtained by means of the necessary cross-validation, but by using the whole benchmark datasets for both training and testing.
no code implementations • 1 Dec 2017 • Nikola Banić, Karlo Koščević, Sven Lončarić
The highest accuracy of color correction is obtained with learning-based color constancy methods, but they require a significant amount of calibrated training images with known ground-truth illumination.
no code implementations • 1 Oct 2013 • Nikola Banić, Sven Lončarić
Therefore we propose a method for estimating global illumination estimation based on local RSR results.