9 citations · 27 across the 19 of their papers we have counts for
20 papers
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…
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…
SUPER: Selfie Undistortion and Head Pose Editing with Identity Preservation
Polina Karpikova, Andrei Spiridonov, Anna Vorontsova +4
Self-portraits captured from a short distance might look unnatural or even unattractive due to heavy distortions making facial features malformed, and ill-placed head poses. In thi…
FAWN: Floor-And-Walls Normal Regularization for Direct Neural TSDF Reconstruction
Anna Sokolova, Anna Vorontsova, Bulat Gabdullin +1
Leveraging 3D semantics for direct 3D reconstruction has a great potential yet unleashed. For instance, by assuming that walls are vertical, and a floor is planar and horizontal, w…
MEDeA: Multi-view Efficient Depth Adjustment
Mikhail Artemyev, Anna Vorontsova, Anna Sokolova +1
The majority of modern single-view depth estimation methods predict relative depth and thus cannot be directly applied in many real-world scenarios, despite impressive performance…
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…
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…
Towards General Purpose Geometry-Preserving Single-View Depth Estimation
Mikhail Romanov, Nikolay Patatkin, Anna Vorontsova +3
Single-view depth estimation (SVDE) plays a crucial role in scene understanding for AR applications, 3D modeling, and robotics, providing the geometry of a scene based on a single…
Training Deep SLAM on Single Frames
Igor Slinko, Anna Vorontsova, Dmitry Zhukov +2
Learning-based visual odometry and SLAM methods demonstrate a steady improvement over past years. However, collecting ground truth poses to train these methods is difficult and exp…
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…
DISCOMAN: Dataset of Indoor SCenes for Odometry, Mapping And Navigation
Pavel Kirsanov, Airat Gaskarov, Filipp Konokhov +7
We present a novel dataset for training and benchmarking semantic SLAM methods. The dataset consists of 200 long sequences, each one containing 3000-5000 data frames. We generate t…
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…