11 citations · 30 across the 17 of their papers we have counts for
21 papers
Neural-field design of broadband Rayleigh-wave carpet cloaks under microstructure realisability constraints
David Aznaurov, Davit Piliposyan, Danila Rukhovich +1
Transformation elasticity provides appropriate material distributions for elastodynamic cloaks but the required stiffness tensors generally violate the minor symmetries of Cauchy e…
Enabling Training-Free Text-Based Remote Sensing Segmentation
Jose Sosa, Danila Rukhovich, Anis Kacem +1
Recent advances in Vision Language Models (VLMs) and Vision Foundation Models (VFMs) have opened new opportunities for zero-shot text-guided segmentation of remote sensing imagery.…
Z3D: Zero-Shot 3D Visual Grounding from Images
Nikita Drozdov, Andrey Lemeshko, Nikita Gavrilov +3
3D visual grounding (3DVG) aims to localize objects in a 3D scene based on natural language queries. In this work, we explore zero-shot 3DVG from multi-view images alone, without r…
Zoo3D: Zero-Shot 3D Object Detection at Scene Level
Andrey Lemeshko, Bulat Gabdullin, Nikita Drozdov +3
3D object detection is fundamental for spatial understanding. Real-world environments demand models capable of recognizing diverse, previously unseen objects, which remains a major…
MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans
Ahmet Serdar Karadeniz, Dimitrios Mallis, Danila Rukhovich +3
Computer-Aided Design (CAD) plays a foundational role in modern manufacturing and product development, often requiring designers to modify or build upon existing models. Converting…
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…
MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Tasks
Jose Sosa, Danila Rukhovich, Anis Kacem +1
Multi-modal data in Earth Observation (EO) presents a huge opportunity for improving transfer learning capabilities when pre-training deep learning models. Unlike prior work that o…
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…
CAD-Recode: Reverse Engineering CAD Code from Point Clouds
Danila Rukhovich, Elona Dupont, Dimitrios Mallis +3
Computer-Aided Design (CAD) models are typically constructed by sequentially drawing parametric sketches and applying CAD operations to obtain a 3D model. The problem of 3D CAD rev…
CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers
Dimitrios Mallis, Ahmet Serdar Karadeniz, Sebastian Cavada +5
We propose CAD-Assistant, a general-purpose CAD agent for AI-assisted design. Our approach is based on a powerful Vision and Large Language Model (VLLM) as a planner and a tool-aug…
How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?
Jose Sosa, Mohamed Aloulou, Danila Rukhovich +4
Self-supervised pre-training has proven highly effective for many computer vision tasks, particularly when labelled data are scarce. In the context of Earth Observation (EO), found…
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…
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…
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…
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…
Learning High-Resolution Domain-Specific Representations with a GAN Generator
Danil Galeev, Konstantin Sofiiuk, Danila Rukhovich +3
In recent years generative models of visual data have made a great progress, and now they are able to produce images of high quality and diversity. In this work we study representa…
IterDet: Iterative Scheme for Object Detection in Crowded Environments
Danila Rukhovich, Konstantin Sofiiuk, Danil Galeev +2
Deep learning-based detectors usually produce a redundant set of object bounding boxes including many duplicate detections of the same object. These boxes are then filtered using n…
MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge
Danila Rukhovich, Danil Galeev
We present a domain adaptation (DA) system that can be used in multi-source and semi-supervised settings. Using the proposed method we achieved 2nd place on multi-source track and…
Estimation of Absolute Scale in Monocular SLAM Using Synthetic Data
Danila Rukhovich, Daniel Mouritzen, Ralf Kaestner +2
This paper addresses the problem of scale estimation in monocular SLAM by estimating absolute distances between camera centers of consecutive image frames. These estimates would im…