11 citations · 38 across the 20 of their papers we have counts for
23 papers
CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
Gennadiy Savrasov, Maksim Elistratov, Nikita Gavrilov +7
Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task. Existing methods can propose CAD operations, but no single source of proposals works eq…
ReText: Text Boosts Generalization in Image-Based Person Re-identification
Timur Mamedov, Karina Kvanchiani, Anton Konushin +1
Generalizable image-based person re-identification (Re-ID) aims to recognize individuals across cameras in unseen domains without retraining. While visual features are sensitive to…
DynaMix: Generalizable Person Re-identification via Dynamic Relabeling and Mixed Data Sampling
Timur Mamedov, Anton Konushin, Vadim Konushin
Generalizable person re-identification (Re-ID) aims to recognize individuals across unseen cameras and environments. While existing methods rely heavily on limited labeled multi-ca…
TUN3D: Towards Real-World Scene Understanding from Unposed Images
Anton Konushin, Nikita Drozdov, Bulat Gabdullin +4
Layout estimation and 3D object detection are two fundamental tasks in indoor scene understanding. When combined, they enable the creation of a compact yet semantically rich spatia…
cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning
Maksim Kolodiazhnyi, Denis Tarasov, Dmitrii Zhemchuzhnikov +6
Computer-Aided Design (CAD) plays a central role in engineering and manufacturing, making it possible to create precise and editable 3D models. Using a variety of sensor or user-pr…
ReMix: Training Generalized Person Re-identification on a Mixture of Data
Timur Mamedov, Anton Konushin, Vadim Konushin
Modern person re-identification (Re-ID) methods have a weak generalization ability and experience a major accuracy drop when capturing environments change. This is because existing…
RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation
Anton Antonov, Andrey Moskalenko, Denis Shepelev +4
The emergence of Segment Anything (SAM) sparked research interest in the field of interactive segmentation, especially in the context of image editing tasks and speeding up data an…
UniDet3D: Multi-dataset Indoor 3D Object Detection
Maksim Kolodiazhnyi, Anna Vorontsova, Matvey Skripkin +2
Growing customer demand for smart solutions in robotics and augmented reality has attracted considerable attention to 3D object detection from point clouds. Yet, existing indoor da…
TETRIS: Towards Exploring the Robustness of Interactive Segmentation
Andrey Moskalenko, Vlad Shakhuro, Anna Vorontsova +5
Interactive segmentation methods rely on user inputs to iteratively update the selection mask. A click specifying the object of interest is arguably the most simple and intuitive i…
OneFormer3D: One Transformer for Unified Point Cloud Segmentation
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin +1
Semantic, instance, and panoptic segmentation of 3D point clouds have been addressed using task-specific models of distinct design. Thereby, the similarity of all segmentation task…
Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data
Nikolay Patakin, Mikhail Romanov, Anna Vorontsova +2
Nowadays, robotics, AR, and 3D modeling applications attract considerable attention to single-view depth estimation (SVDE) as it allows estimating scene geometry from a single RGB…
Independent Component Alignment for Multi-Task Learning
Dmitry Senushkin, Nikolay Patakin, Arseny Kuznetsov +1
In a multi-task learning (MTL) setting, a single model is trained to tackle a diverse set of tasks jointly. Despite rapid progress in the field, MTL remains challenging due to opti…
Contour-based Interactive Segmentation
Danil Galeev, Polina Popenova, Anna Vorontsova +1
Recent advances in interactive segmentation (IS) allow speeding up and simplifying image editing and labeling greatly. The majority of modern IS approaches accept user input in the…
Top-Down Beats Bottom-Up in 3D Instance Segmentation
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin +1
Most 3D instance segmentation methods exploit a bottom-up strategy, typically including resource-exhaustive post-processing. For point grouping, bottom-up methods rely on prior ass…
TR3D: Towards Real-Time Indoor 3D Object Detection
Danila Rukhovich, Anna Vorontsova, Anton Konushin
Recently, sparse 3D convolutions have changed 3D object detection. Performing on par with the voting-based approaches, 3D CNNs are memory-efficient and scale to large scenes better…
Floorplan-Aware Camera Poses Refinement
Anna Sokolova, Filipp Nikitin, Anna Vorontsova +1
Processing large indoor scenes is a challenging task, as scan registration and camera trajectory estimation methods accumulate errors across time. As a result, the quality of recon…
FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection
Danila Rukhovich, Anna Vorontsova, Anton Konushin
Recently, promising applications in robotics and augmented reality have attracted considerable attention to 3D object detection from point clouds. In this paper, we present FCAF3D…
ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
Danila Rukhovich, Anna Vorontsova, Anton Konushin
In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem. To address this problem, we propose ImVoxelNet, a novel full…
Decoder Modulation for Indoor Depth Completion
Dmitry Senushkin, Mikhail Romanov, Ilia Belikov +2
Depth completion recovers a dense depth map from sensor measurements. Current methods are mostly tailored for very sparse depth measurements from LiDARs in outdoor settings, while…
Measuring robustness of Visual SLAM
David Prokhorov, Dmitry Zhukov, Olga Barinova +2
Simultaneous localization and mapping (SLAM) is an essential component of robotic systems. In this work we perform a feasibility study of RGB-D SLAM for the task of indoor robot na…
Scene Motion Decomposition for Learnable Visual Odometry
Igor Slinko, Anna Vorontsova, Filipp Konokhov +2
Optical Flow (OF) and depth are commonly used for visual odometry since they provide sufficient information about camera ego-motion in a rigid scene. We reformulate the problem of…
Double Refinement Network for Efficient Indoor Monocular Depth Estimation
Nikita Durasov, Mikhail Romanov, Valeriya Bubnova +2
Monocular depth estimation is the task of obtaining a measure of distance for each pixel using a single image. It is an important problem in computer vision and is usually solved u…
Pose-based Deep Gait Recognition
Anna Sokolova, Anton Konushin
Human gait or walking manner is a biometric feature that allows identification of a person when other biometric features such as the face or iris are not visible. In this paper, we…