A tutorial explaining a machine vision model that emulates human performance when it recovers natural 3D scenes from 2D images

Li Y.; T. Sawada; Latecki L. J.; Steinman R. M.; Pizlo Z.

Publications

?

A tutorial explaining a machine vision model that emulates human performance when it recovers natural 3D scenes from 2D images

Journal of Mathematical Psychology. 2012. Vol. 56. No. 4. P. 217–231.

Li Y., Sawada T., Latecki L. J., Steinman R. M., Pizlo Z.

Research target: Psychology Computer Science

Priority areas: humanitarian IT and mathematics engineering science

Language: English

Text on another site

Keywords: visual perception computer vision SPACE PERCEPTION robotic vision 3D perception object and scene perception

Non-linear in-band interference cancellation on base of conjugate gradients method

Degtyarev A., Bakhurin S., Yudin N., DSPA 2026 P. 1–6

This paper investigates one possible solution to the problem of self-interference cancellation (SIC) arising in the design of in-band full-duplex (IBFD) communication systems. Self-interference cancellation is performed in the digital domain using multilayer nonlinear models adapted via gradient-based optimization. The presence of local minima and saddle points during the adaptation of multilayer models limits the ...

Added: May 26, 2026

Heritability of Functional Literacy: Evidence from a Classical Twin Design

Kolachev N., Kovaleva G., Behavior Genetics 2026

Functional literacy—the ability to apply reading, mathematical, and scientific knowledge in authentic contexts as operationalized by the PISA framework—is a key predictor of educational attainment, labour-market outcomes, and economic growth. Despite extensive behavioral-genetic research on cognitive ability, the heritability of competency-based literacy measures remains largely unexamined, particularly outside Western populations. The present study addresses this ...

Added: May 26, 2026

Comparative Study of Training Methods and Architectures of Echo State Networks

Androsov I., Proceedings of the Institute for System Programming of the RAS 2026 Vol. 38 No. 3 P. 87–114

This paper examines echo state networks (ESNs), one of the most prevalent approaches to implementing reservoir computing. An ESN consists of a recurrent neural network with fixed (untrained) weights and a readout layer that is typically linear and trainable. This approach enables the creation of energyefficient and computationally efficient neural networks capable of real-time learning. However, since ...

Added: May 26, 2026

How virtual urban green spaces influence stress and risk-taking

Dorri Sedeh S., Kosonogov V., Kerimova N. et al., Frontiers in Psychology 2026 Vol. 17 Article 1710257

Introduction: As cities continue to grow, access to natural environments is becoming more limited, contributing to increased stress levels in urban populations. Panoramic 360° videos provide a creative and scalable means of simulating natural environments, potentially reducing stress in city residents under controlled settings. Here, we examined whether short immersive experiences in different urban environments support ...

Added: May 25, 2026

Novelty, Category and Orientation Tuning for Printed Characters: A Magnetoencephalography Study with Fast Periodic Visual Stimulation

Kochetkova Ekaterina, Kostanian D., Martynova O. et al., Brain Topography 2026 Vol. 39 No. 4 Article 51

Letter recognition is assumed to involve several levels of analysis, including coarse tuning for category and novelty and more fine tuning for specific features, related to letter orientation. We employed an oddball fast periodic visual stimulation (FPVS) paradigm with magnetoencephalography (Elekta VectorView, 306 sensors) to study neural discrimination responses in the source space. Using contrasts ...

Added: May 24, 2026

Рефакторинг исходного кода на основе LLM и расширения UML

Караваева Е. А., Кулигин Л. А., Rezunik L. et al., Труды Института системного программирования РАН 2026 Т. 38 № 3 С. 67–94

В статье представлен метод рефакторинга исходного кода на основе интеграции большой языковой модели (LLM) и расширенной UML-модели программного кода. Предложенный подход позволяет выявлять проблемные участки кода с использованием функций тревожности и структурных метрик классов, а затем выполнять автоматизированный рефакторинг. Ключевой особенностью метода является использование LLM для генерации формальных спецификаций на языке OCL (Object Constraint Language), ...

Added: May 24, 2026

Coping with AI errors with provable guarantees

Tyukin I., Tyukina T., van Helden D. P. et al., Information Sciences 2024 Vol. 678 Article 120856

AI errors pose a significant challenge, hindering real-world applications. This work introduces a novel approach to cope with AI errors using weakly supervised error correctors that guarantee a specific level of error reduction. Our correctors have low computational cost and can be used to decide whether to abstain from making an unsafe classification. We provide ...

Added: May 23, 2026

Overcoming the Curse of Dimensionality with Synolitic AI

Zaikin A., Sviridov I., Sosedka A. et al., Technologies 2026 Vol. 14 No. 2 Article 84

High-dimensional tabular data are common in biomedical and clinical research, yet conventional machine learning methods often struggle in such settings due to data scarcity, feature redundancy, and limited generalization. In this study, we systematically evaluate Synolitic Graph Neural Networks (SGNNs), a framework that transforms high-dimensional samples into sample-specific graphs by training ensembles of low-dimensional pairwise ...

Added: May 23, 2026

Stable On-the-Fly Learning for Dynamic Neural Networks With Delayed Inputs

Kibkalo Vladislav, Chertopolokhov V., Mukhamedov A. et al., IEEE Access 2026 Vol. 14 P. 14369–14392

This study presents on-the-fly identification and multi-step prediction of nonlinear systems with delayed inputs using a dynamic neural network combined with a smooth projection onto ellipsoids. The projection enforces parameter constraints that guarantee stability, while a Lyapunov–Krasovskii analysis yields computable ultimate error bounds. Riccati-type matrix inequalities are derived, providing an efficient vectorization–projection–devectorization implementation suitable for ...

Added: May 22, 2026

Опыт применения сетевого анализа (SNA) в историческом нарративе полисубъектного региона (на примере валлийской хроники Brut y Tywysogyon)

Loshkareva M. E., Matveeva N., Вестник Томского государственного университета. История 2026 № 100 С. 112–118

This research is an endeavor to apply social network analysis (SNA) to the study of a medieval narrative source. The authors suppose that the use of network analysis may offer new possibilities in the study of the history of regions characterized by some political fragmentation. Authors tried to construct networks of historical interactions from 1193 ...

Added: May 22, 2026

Embodied language and early motor restriction: evidence from children with obstetric brachial plexus palsy and arthrogryposis

Kadieva D., Blagoveshchensky E., Agranovich O. et al., Frontiers in Psychology 2026 Vol. 17 Article 1832623

Embodied and embedded cognition (EEC) theory proposes that language and cognitive development emerge from bodily interactions with the environment, yet empirical tests of this claim in clinical developmental populations remain rare. This mini-review synthesizes behavioral, electrophysiological, and structural neuroimaging evidence from children with serious early motor disorders—obstetric brachial plexus palsy and arthrogryposis multiplex congenita—which restrict ...

Added: May 20, 2026

Влияние стресс-факторов городской среды на психическое здоровье: обзор зарубежных исследований

Кияненко И. К., Клиническая и специальная психология 2026 Т. 15 № 1 С. 7–19

Context and relevance. The problem of the impact of urban stress factors on mental health is becoming increasingly relevant in the context of urbanization. Living in cities is accompanied by increased psychophysiological stress, which leads to an increase in the prevalence of mental disorders among urban residents. Objective. The purpose of the article is to ...

Added: May 19, 2026

ML-based Fast Simulation of FARICH Responses

Shipilov F., Barnyakov A., Ivanov A. et al., / Series Physics "arxiv.org". 2026.

A fast simulation of the detector response is a vital task in high-energy physics (HEP). Traditional Monte-Carlo methods form the backbone of modern particle physics simulation software but are computationally expensive. We present a machine-learning-based approach to fast simulation of the Focusing Aerogel Ring Imaging Cherenkov (FARICH) detector response. Given a particle track and momentum, ...

Added: May 19, 2026

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)

Rabat: Association for Computational Linguistics, 2026.

Added: May 19, 2026

Dataset of solubility values for organic compounds in binary mixtures of solvents at various temperatures

Bezzubov S., Malikov D., Krasnov L. et al., Scientific data 2026 Vol. 13 Article 727

Solubility is a crucial property of organic compounds, impacting their potential applications in synthetic chemistry, materials science and drug design. Moreover, in technological processes mixtures of solvents are often utilized, making the solubility assessment more complicated. Predicting solubility values in mixtures of solvents from a molecular structure can help to address this issue, although a ...

Added: May 19, 2026

Aerokinesis: An IoT-Based Vision-Driven Gesture Control System for Quadcopter Navigation Using Deep Learning and ROS2

Pikalov V., Meshcheryakov V., Kondratev S. et al., Technologies 2026 Vol. 14 No. 1 P. 1–27

This paper presents Aerokinesis, an IoT-based software–hardware system for intuitive gesture-driven control of quadcopter unmanned aerial vehicles (UAVs), developed within the Robot Operating System 2 (ROS2) framework. The proposed system addresses the challenge of providing an accessible human–drone interaction interface for operators in scenarios where traditional remote controllers are impractical or unavailable. The architecture comprises ...

Added: May 19, 2026

Aerokinesis: An IoT-Based Vision-Driven Gesture Control System for Quadcopter Navigation Using Deep Learning and ROS2

Kondratev S., Yulia Dyrchenkova, Georgiy Nikitin et al., Technologies 2026 Vol. 14 No. 1 Article 69

Added: May 19, 2026

General and Specific Facets of Anxiety: Psychometric Analysis and Impact on Cognitive Performance

Alenina E., Kristina Terenteva, Kosonogov V., Behavioral Sciences 2026 Vol. 16 No. 5 Article 806

Anxiety is a multidimensional construct that influences cognitive performance in complex ways, yet its factor structure and domain-specific effects remain unclear. This study examined (1) the psychometric structure of general and specific anxiety measures, (2) their associations with cognitive performance across different domains, and (3) the predictive power of machine learning models in classifying cognitive ...

Added: May 18, 2026

Perovskite nanoparticles Cs4PbBr6 and CsPbBr3: synthesis, analysis and peculiar optical properties

Гущина В. А., / Series chemrxiv-2023-vpzhz-v2 "ChemRxiv". 2023.

All-inorganic perovskite CsPbBr3 and Cs4PbBr6 nanoparticles are being intensively studied due to their unique properties and wide range of applications; however, however, the nature of their optical properties is not yet fully understood due to the difficulty of synthesis of singlephase nanoparticles. In this article we describe the features of the synthesis of single-phase particles ...

Added: May 14, 2026

Natural hazard database from Internet publications: text mining with a large language model

Derkacheva A., Sakirkina M., Kraev G. et al., /. 2026.

Comprehensive data on natural hazards and their consequences are crucial for effective for risk assessment, adaptation planning, and emergency response. However, many countries face challenges with fragmented, inconsistent, and inaccessible data, particularly regarding local-scale events. To address this data gap in Russia, we developed an end-to-end processing pipeline that scrapes news from various online sources, ...

Added: April 28, 2026

Школьный литературный канон эмиграции 1918–1939 гг.

Strizhkova D., / Институт русской литературы (Пушкинский Дом) РАН. Серия B001 "Репозиторий открытых данных по русской литературе и фольклору". 2026.

В базе данных представлена роспись русскоязычных литературных произведений и отрывков, напечатанных в учебниках по словесности, хрестоматиях, книгах для чтения, сборниках стихотворений и рассказов, выходивших во Франции, Германии, Латвии, Эстонии, Болгарии, Сербии в период первой волны русской эмиграции с 1918 по 1939 гг. Датасет представляет интерес для исследователей школьного литературного канона, эмиграции и детского чтения ...

Added: April 22, 2026

Algorithmic overlaps as thermodynamic variables: from local to cluster Monte Carlo dynamics in critical phenomena

Pilé I., Deng Y., Shchur L., / Series arXiv "math". 2026. No. 2604.10254.

We investigate the spatial overlap of successive spin configurations in Markov chain Monte Carlo simulations using the local Metropolis algorithm and the Svendsen-Wang and Wolff cluster algorithms. We examine the dynamics of these algorithms for two models in different universality classes: the Ising model and the Potts model with three components. The overlap of two ...

Added: April 20, 2026

Современная российская мультипликация как инструмент воспитания традиционных духовно-нравственных ценностей

Жигунов А. Ю., / Basic Research Programme. Серия HUM "Humanities". 2026. № 1.

The article attempts to describe the features of the educational potential of Russian animation programmes in aspect of the representation of traditional spiritual and moral values. Based on media and semiotic analysis, the method of cultural and historical interpretation, animated Russian projects created from 2000 to the 2025, which were translated on television channels or streaming ...

Added: April 19, 2026

Using predefined vector systems to speed up neural network multimillion class classification

Gabdullin N., Androsov I., / Series Computer Science "arxiv.org". 2026.

Label prediction in neural networks (NNs) has O(n) complexity proportional to the number of classes. This holds true for classification using fully connected layers and cosine similarity with some set of class prototypes. In this paper we show that if NN latent space (LS) geometry is known and possesses specific properties, label prediction complexity can ...

Added: April 2, 2026