arXiv subjects

Sergey Korchagin

Publications and source records attributed to Sergey Korchagin.

6 recordsLinked to original sources

arXiv2026

An acousto-optic colorimeter for color psychophysics

A complete model of human color perception requires the ability to present any color as a stimulus.Most existing measurements were collected with physical color samples, and current laboratory generators, such as displays and multi-primary LED systems, work with a small number of fixed primaries. Published color-difference data therefore cover about 40\% of the CIE~$xy$ chromaticity diagram, while commercial wide-gamut displays already reach two thirds of it and need difference metrics there. We describe an acousto-optic colorimeter that lets the experimenter choose the primaries. The device selects up to four narrow bands from a supercontinuum (white-light) laser, each with electronically set wavelength and intensity, and covers 95\% of the CIE~$xy$ chromaticity diagram. Threshold-scale color differences, presented in alternation as in a discrimination experiment, are reproduced with a mean error of 0.08--0.12 CIEDE2000 units ($ΔE_{00}$) at five CIE-recommended color centers. Because one color can be built from many combinations of narrow bands, the bands are chosen for the task: the finest adjustment for color matching, the least disagreement between observers for color-difference measurement. In simulations with 151~individual observers from a published dataset, with these bands observers see colors 0.6--1.9~$ΔE_{00}$ from the intended one on average, against 1.2--2.5~$ΔE_{00}$ on a calibrated wide-gamut LCD, lower at every center. The approach applies to any narrowband source and lets experimenters use saturated colors while limiting the effect of individual differences in color vision.

physics.optics↗

arXiv2026

An Acousto-Optic Colorimeter

Uniform color spaces and color-difference formulae rest on visual data obtained almost entirely with surface samples and conventional displays, whose primaries confine the measurements to a limited chromaticity range. The highly saturated region of color space is therefore the least measured part of human color perception, at the moment when quantum-dot, microLED, and laser displays have begun to operate inside it. Closing this gap requires stimuli more saturated than any fixed-primary device can produce, together with the stability and uniformity demanded by visual experiments. We present an acousto-optic colorimeter built for this purpose. A four-channel acousto-optic tunable filter selects narrow spectral components from a supercontinuum laser over the calibrated range of 443--660~nm, with measured linewidths of 1.37--3.20~nm; the wavelength and radiance of every component are set electronically, so the primary set itself becomes an experimental variable. A compact diffuser--light-pipe homogenizer combines the selected components into a uniform observation field, and spectral feedback stabilizes their intensities. The calibrated primary set covered 95\% of the area enclosed by the CIE 1964 $10^{\circ}$ spectral locus in the $x,y$ chromaticity plane. The calculated maximum luminance reached 1406~cd\,m$^{-2}$, with 328~cd\,m$^{-2}$ available at the gray Robertson chromaticity. Across an 18-mm observation field the mean spatial $ΔE_{00}$ difference was 0.913, and five Robertson color centers reproduced under continuous feedback gave mean target errors of 0.34--1.26~$ΔE_{00}$ over 10-min intervals. The instrument thus delivers calibrated, uniform, and stable highly saturated stimuli, and is intended to extend the empirical basis of color-difference measurement into the region where data are still absent.

physics.optics↗

arXiv2026

NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge

This paper presents a review of the NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge. The objective of the competition was to merge a set of misaligned smartphone images in the raw domain, captured in low-light conditions, into a single, clean image. Introduced setup simultaneously addresses two problems of low-light photography: visual degradations such as high noise and mixed scene illuminants, and the geometric inconsistencies caused by hand movement during multi-frame capture. To advance research in low-light and nighttime computational photography, a challenging dataset was collected comprising 585 real-world scenes, spanning indoor low-light and outdoor nighttime conditions, for training and benchmarking participant solutions. The competition employed a three-stage evaluation protocol: automatic validation via the CodaBench platform in stages one and two, followed by blind assessment on a private test set for the final ranking. Ten teams surpassed the established baseline, achieving improvements of up to +6.49 dB in PSNR and +0.0101 in SSIM, thereby establishing new state-of-the-art performance for burst-based low-light image enhancement. These results demonstrate significant progress in handling real-world noise, motion, and illumination variability in the low-light setting. Comprehensive results, leaderboards, and additional information are publicly available at https://nightimaging.org.

cs.CV↗

arXiv2026

Enhancing the Reliability of Medical AI through Expert-guided Uncertainty Modeling

Artificial intelligence (AI) systems accelerate medical workflows and improve diagnostic accuracy in healthcare, serving as second-opinion systems. However, the unpredictability of AI errors poses a significant challenge, particularly in healthcare contexts, where mistakes can have severe consequences. A widely adopted safeguard is to pair predictions with uncertainty estimation, enabling human experts to focus on high-risk cases while streamlining routine verification. Current uncertainty estimation methods, however, remain limited, particularly in quantifying aleatoric uncertainty, which arises from data ambiguity and noise. To address this, we propose a novel approach that leverages disagreement in expert responses to generate targets for training machine learning models. These targets are used in conjunction with standard data labels to estimate two components of uncertainty separately, as given by the law of total variance, via a two-ensemble approach, as well as its lightweight variant. We validate our method on binary image classification, binary and multi-class image segmentation, and multiple-choice question answering. Our experiments demonstrate that incorporating expert knowledge can enhance uncertainty estimation quality by $9\%$ to $50\%$ depending on the task, making this source of information invaluable for the construction of risk-aware AI systems in healthcare applications.

cs.LG↗

arXiv2024

Expert-aware uncertainty estimation for quality control of neural-based blood typing

In medical diagnostics, accurate uncertainty estimation for neural-based models is essential for complementing second-opinion systems. Despite neural network ensembles' proficiency in this problem, a gap persists between actual uncertainties and predicted estimates. A major difficulty here is the lack of labels on the hardness of examples: a typical dataset includes only ground truth target labels, making the uncertainty estimation problem almost unsupervised. Our novel approach narrows this gap by integrating expert assessments of case complexity into the neural network's learning process, utilizing both definitive target labels and supplementary complexity ratings. We validate our methodology for blood typing, leveraging a new dataset "BloodyWell" unique in augmenting labeled reaction images with complexity scores from six medical specialists. Experiments demonstrate enhancement of our approach in uncertainty prediction, achieving a 2.5-fold improvement with expert labels and a 35% increase in performance with estimates of neural-based expert consensus.

cs.CV↗

arXiv2024

NTIRE 2024 Challenge on Night Photography Rendering

This paper presents a review of the NTIRE 2024 challenge on night photography rendering. The goal of the challenge was to find solutions that process raw camera images taken in nighttime conditions, and thereby produce a photo-quality output images in the standard RGB (sRGB) space. Unlike the previous year's competition, the challenge images were collected with a mobile phone and the speed of algorithms was also measured alongside the quality of their output. To evaluate the results, a sufficient number of viewers were asked to assess the visual quality of the proposed solutions, considering the subjective nature of the task. There were 2 nominations: quality and efficiency. Top 5 solutions in terms of output quality were sorted by evaluation time (see Fig. 1). The top ranking participants' solutions effectively represent the state-of-the-art in nighttime photography rendering. More results can be found at https://nightimaging.org.

cs.CV↗