← Back to home03 / Publications

Publications.

Selected work, the complete publication list, and patents.

Selected and recent work

arXiv2026

CADENA: Stepwise CAD Reverse Engineering

S. Kabisov, G. Savrasov, M. Elistratov, A. Rodriguez, D. Ignatiev, N. Gavrilov, R. Uzdenov, A. Boyko, I. Pasechnik, A. Konushin, A. Kuznetsov, D. Zhemchuzhnikov

Builds an editable CAD model step by step, checking geometry after each operation.

CVPR Findings2026

CADReasoner: Iterative Program Editing for CAD Reverse Engineering

S. Kabisov, V. Kirichuk, A. Volkov, G. Savrasov, M. Barannikov, A. Konushin, A. Kuznetsov, D. Zhemchuzhnikov

Iteratively edits a CAD program using feedback from geometric discrepancies.

ICLR2026

cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning

M. Kolodiazhnyi, D. Tarasov, D. Zhemchuzhnikov, A. Nikulin, I. Zisman, A. Vorontsova, A. Konushin, V. Kurenkov, D. Rukhovich

Reconstructs CAD models from images, point clouds, and text with online reinforcement learning.

ICRA2026

TUN3D: Towards Real-World Scene Understanding from Unposed Images

A. Konushin, N. Drozdov, B. Gabdullin, A. Zakharov, A. Vorontsova, D. Rukhovich, M. Kolodiazhnyi

Estimates room layout and objects from images without known camera poses.

CVPR2026

Zoo3D: Zero-Shot 3D Object Detection at Scene Level

A. Lemeshko, B. Gabdullin, N. Drozdov, A. Konushin, D. Rukhovich, M. Kolodiazhnyi

Detects unseen 3D object categories across a scene without category-specific training.

ACL2026

Z3D: Zero-Shot 3D Visual Grounding from Images

N. Drozdov, A. Lemeshko, N. Gavrilov, A. Konushin, D. Rukhovich, M. Kolodiazhnyi

Locates a described object in a 3D scene using images.

AAAI2025

UniDet3D: Multi-dataset Indoor 3D Object Detection

M. Kolodiazhnyi, A. Vorontsova, M. Skripkin, D. Rukhovich, A. Konushin

A unified indoor 3D detector trains across multiple datasets.

CVPR2024

OneFormer3D: One Transformer for Unified Point Cloud Segmentation

M. Kolodiazhnyi, A. Vorontsova, A. Konushin, D. Rukhovich

One transformer handles semantic, instance, and panoptic point-cloud segmentation.

ECCV2022

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

D. Rukhovich, A. Vorontsova, A. Konushin

A fully convolutional method detects 3D objects without anchor boxes.

IJCAI2026

Unified Sensor Simulation for Autonomous Driving

N. Patakin, A. Shirokov, A. Konushin, D. Senushkin

A unified model simulates camera and LiDAR readings for autonomous driving.

Neurocomputing2026

DynaMix: Generalizable Person Re-Identification via Dynamic Relabeling and Mixed Data Sampling

T. Mamedov, A. Konushin, V. Konushin

Improves generalizable person re-identification through relabeling and mixed data sampling.

ICIP2022

Reviving Iterative Training with Mask Guidance for Interactive Segmentation

K. Sofiiuk, I. Petrov, A. Konushin

Interactive segmentation refines an object mask from user clicks.

All publications

2026

  • HieFormer: Leveraging Hyperbolic Geometry to Overcome the Hierarchical Expressiveness Limitation of Transformers
  • GAGAN: Geometry-aware generative adversarial network with progressive refinement for point cloud completion
  • HFF-BiG: Hierarchical feature fusion with bi-directional gating for 3D indoor instance segmentation
  • DynaMix: Generalizable person re-identification via dynamic relabeling and mixed data sampling
  • Распознавание фальшивых видео с подменой лица с помощью учета направления взгляда человека
  • cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning
  • TUN3D: Towards Real-World Scene Understanding from Unposed Images
  • Zoo3D: Zero-Shot 3D Object Detection at Scene Level
  • Z3D: Zero-Shot 3D Visual Grounding from Images
  • Visual Implicit Geometry Transformer for Autonomous Driving
  • Unified Sensor Simulation for Autonomous Driving
  • CADReasoner: Iterative Program Editing for CAD Reverse Engineering
  • CADENA: Stepwise CAD Reverse Engineering
  • CADEvolve: Creating Realistic CAD via Program Evolution
  • ReText: Text Boosts Generalization in Image-Based Person Re-identification

2025

2024

  • RClicks: realistic click simulation for benchmarking interactive segmentation
  • Oneformer3d: One transformer for unified point cloud segmentation
  • Нейросетевые методы сегментации изображений высокого разрешения
  • Features fusion for dual-view mammography mass detection
  • Tetris: Towards exploring the robustness of interactive segmentation
  • Top-down beats bottom-up in 3d instance segmentation
  • Практическое приложение методов многокритериальной оптимизации к задаче релокализации камеры

2023

2022

2021

  • Decoder modulation for indoor depth completion
  • Queue waiting time estimation using person re-identification by upper body
  • The Improvement of Segmentation of Lung Pathologies and Pleural Effusion on CT-scans of Patients with Covid-19
  • Learning high-resolution domain-specific representations with a gan generator
  • Iterdet: iterative scheme for object detection in crowded environments
  • Foreground-aware semantic representations for image harmonization
  • Road images augmentation with synthetic traffic signs using neural networks
  • Operator’s gaze direction recognition
  • Practical People Counting Algorithm
  • Automatic detection of certain unwanted driver behavior
  • Rare Traffic Signs Recognition

2020

  • Self-supervised visual odometry with ego-motion sampling
  • Towards general purpose geometry-preserving single-view depth estimation
  • f-brs: Rethinking backpropagating refinement for interactive segmentation
  • Classification of rare traffic signs
  • Neural Network Model for Face Recognition from Dynamic Vision Sensor
  • Bladder semantic segmentation
  • Pairwise Ranking Distillation for Deep Face Recognition
  • Algorithm for Counting Cars in Large-scale Video Surveillance Systems
  • Improving the Neural Network Algorithm for Assessing the Quality of Facial Images
  • A distributed tracking algorithm for counting people in video by head detection
  • Data distillation for traffic sign detection
  • Camera parameters estimation from pose detections
  • Segmentation of Lungs, Lesions, and Lesion Types on Chest CT Scans of Patients with Covid-19

2019

  • Face anti-spoofing with joint spoofing medium detection and eye blinking analysis
  • Методы идентификации человека по походке в видео
  • Rare traffic sign recognition using synthetic training data
  • View resistant gait recognition
  • Training deep SLAM on single frames
  • Perceptual image anomaly detection
  • Double refinement network for room layout estimation
  • Double refinement network for efficient monocular depth estimation
  • Discoman: Dataset of indoor scenes for odometry, mapping and navigation
  • Fine-tuning SMPL: A Framework for Highly Detailed Statistical Human Model Building
  • Adaptis: Adaptive instance selection network
  • Scene motion decomposition for learnable visual odometry
  • A distributed tracking algorithm for counting people in video
  • Methods of gait recognition in video
  • Measuring robustness of visual slam
  • Human identification by gait from event-based camera
  • Face recognition with low false positive error rate
  • A semi-automatic method of collecting samples for learning a face identification algorithm
  • Pose‐based deep gait recognition

2018

  • Speech Separation and Recognition Using CASA Segmentation and Language-Based Grouping
  • Deep probabilistic human pose estimation
  • Human recognition by appearance and gait
  • Обзор методов распознавания человека по походке в видео
  • Синтез изображений дорожных знаков с помощью условных порождающих противоборствующих нейросетей
  • Распределённый алгоритм сопровождения людей в видео
  • Синтез обучающих выборок для классификации дорожных знаков с помощью нейросетей

2017

  • Markov chain Monte Carlo based video tracking algorithm
  • Gait recognition based on convolutional neural networks
  • Convolutional neural network for camera pose estimation from object detections
  • Constructing a speech audio–video corpus by aligning long segments of speech and text
  • Background subtraction with convolutional neural network and oversegmentation
  • Automatic calibration of surveillance video camera
  • Gait recognition based on relative distance and motion features
  • Глубинные двоичные дескрипторы изображения человека для его повторной идентификации и сопровождения в видео
  • Abandoned Objects Detection in Video Sequences
  • Использование геометрии сцены для увеличения точности детекторов

2016

  • Estimation of the people position in the world coordinate system for video surveillance
  • Background subtraction using a convolutional neural network
  • Further improvement on an MCMC-based video tracking algorithm
  • Fire and Smoke Detection in Video Sequences
  • Подавление ложноположительных обнаружений лиц в видеопотоках систем видеонаблюдения
  • Российская база изображений автодорожных знаков

2015

  • Последовательная половая и возрастная классификация людей по изображению лица на основе ранжированных локальных бинарных шаблонов
  • Simultaneous classification of several features of a person’s appearance using a deep convolutional neural network
  • An improvement on an MCMC-based video tracking algorithm
  • Human pose estimation in video via MCMC sampling
  • An algorithm for estimating locations of people in world coordinates and its application for tracking
  • Подсчет количества людей в видеопоследовательности на основе детектора головы человека

2014

  • Modification of the multi-target tracking algorithm based on energy minimization
  • Face quality assessment for face verification in video

2013

  • The matching of infrared markers for tracking objects using stereo pairs
  • Evaluation of traffic sign recognition methods trained on synthetically generated data
  • Simultaneous facial attribute classification with convolutional neural networks
  • Определение типов объектов в видеопотоке с камеры наблюдения на основе покадровой классификации
  • Система автоматического картографирования знаков дорожного движения
  • Сопровождение людей в системах многокамерного видеонаблюдения для спортивных игр
  • A system for large-scale automatic traffic sign recognition and mapping.
  • Классификация людей по изображению лица на основе сравнительных признаков
  • Возрастная классификация людей по изображению лица на основе метода ранжирования и локальных бинарных шаблонов
  • Эксперименты с обучением методов распознавания дорожных знаков на синтетических данных
  • Improvement of MCMC-based video tracking algorithm

2012

  • Alpha-flow for video matting
  • A method for traffic sign detection in an image with learning from synthetic data
  • Система бесконтактных измерений параметров движения высокоскоростных объектов
  • Каскадный алгоритм для отслеживания лица человека в видеопотоке
  • Бесконтактные измерения характеристик движения объекта с использованием инфракрасных маркеров
  • Алгоритм плотной стереореконструкции на основе контрольных точек и разметки плоскостями
  • Семантическая сегментация данных лазерного сканирования
  • Модификация алгоритма классификации возраста людей по изображению лица на основе метода ранжирования
  • Выделение объектов в видеопотоке на основе разрезов графов
  • Многокадровый оптический поток на основе траекторий
  • Реконструкция траектории движения и формы объекта с использованием инфракрасных маркеров и стереопары
  • Simile Classifiers for Face Classification

2011

  • Reconstruction of structure and texture of city building facades
  • People Tracking Algorithm for Human Height Mounted Cameras
  • Infrared marker matching for object tracking in stereo setup
  • Алгоритм слежения за людьми для построения интеллектуального интерфейса человек-компьютер на основе фильтра частиц

2010

  • Поверхностная визуализация данных об экспресии генов в коре головного мозга и гиппокампе мозга мыши
  • Устойчивые алгоритмы оценки параметров модели на основе случайных выборок
  • Поиск регулярных решеток на текстуре фасадов зданий
  • An algorithmfor clothes-based human recognition in video
  • Построение трехмерной модели порового пространства горных пород
  • Алгоритм распознавания людей в видеопоследовательности на основе случайных патчей
  • Отслеживание контура лабораторной мыши в видеопоследовательности на основе метода ветвей и границ
  • Improvement of background subtraction by mask constraints
  • Automatic Extraction of Regular Grids from Rectified Facade Image

2009

  • Document images geometrical distortions correction using text lines shape extraction
  • Robust LIDAR data segmentation using compact point clusters
  • Автоматическая сегментация облаков точек на основе элементов поверхности
  • VIDEO TRACKING AND BEHAVIOUR SEGMENTATION OF LABORATORY RODENTS
  • Очищение текстур фасадов зданий с использованием их структуры
  • Adaptation of mouse brain gene expression data for further Statistical Parametrical Mapping analysis
  • Efficient road mapping via interactive image segmentation

2008

  • Fast automatic single-view 3-d reconstruction of urban scenes
  • Video tracking of laboratory rodents with active shape models
  • Behavior video tracking system with automatic segmentation into behaviorial acts
  • Выбор объектов для обучения в условиях сильной несбалансированности классов
  • Алгоритмы детектирования разметки и дефектов дорожного покрытия
  • Semantic segmentation of road images based on cascade classifiers

2007

  • Interactive image-based urban modeling

2006

  • Геометрические свойства нескольких изображений
  • Подгонка параметрических моделей к облакам трехмерных точек
  • Image-based 3D Reconstruction of Generalized Box with User Sketches
  • Extending RANSAC-based estimators to handle unknown and varying noise level
  • Guided Quasi-Dense Tracking for 3D Reconstruction

2005

  • Combined guided tracking and matching with adaptive track initialization
  • AMLESAC: A new maximum likelihood robust estimator

2004

  • Depth image-based representation and compression for static and animated 3-D objects
  • Обзор робастных схем оценки параметров моделей на основе случайных выборок
  • Отслеживание точечных особенностей в видеопоследовательностях с изменениями резкости

2003

  • A framework for depth image-based modeling and rendering

2002

  • Depth image-based representations for static and animated 3D objects

Patents

  • RU2842113C1Method for combined segmentation of cloud of 3d points2025-06-20Patent
  • US12238422B2Method of constructing front panorama of shelving from arbitrary series of frames based on shelving 3D model2025-02-25Patent
  • RU2833268C1Interactive image segmentation2025-01-16Patent
  • US20240420363A1Floorplan-aware camera pose refinement method and system2024-12-19Patent
  • US20230121534A1Method and electronic device for 3d object detection using neural networks2023-04-20Patent
  • US11514694B2Teaching GAN (generative adversarial networks) to generate per-pixel annotation2022-11-29Patent
  • RU2761768C1Method for estimating the depth of a scene based on an image and computing apparatus for implementation thereof2021-12-13Patent
  • RU2742701C1Method for interactive segmentation of object on image and electronic computing device for realizing said object2021-02-09Patent
  • US8896665B2Camera calibration method and medium and 3D object reconstruction method and medium using the same2014-11-25Patent
  • US8681150B2Method, medium, and system with 3 dimensional object modeling using multiple view points2014-03-25Patent
  • US8395824B2Method for determining ground line2013-03-12Patent
  • RU2470368C2Image processing method2012-12-20Patent
  • US8254667B2Method, medium, and system implementing 3D model generation based on 2D photographic images2012-08-28Patent
  • US8189031B2Method and apparatus for providing panoramic view with high speed image matching and mild mixed color blending2012-05-29Patent
  • US7899270B2Method and apparatus for providing panoramic view with geometric correction2011-03-01Patent
  • US7453455B2Image-based rendering and editing method and apparatus2008-11-18Patent