{"total":82,"rows":[{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575,"area":null},{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196,"area":null},{"id":"2203.10421","title":"CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation","created":"2022-03-20","cited_by_count":194,"area":null},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144,"area":null},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2305.02743","title":"Incremental 3D Semantic Scene Graph Prediction from RGB Sequences","created":"2023-05-04","cited_by_count":39,"area":null},{"id":"2108.09481","title":"DSP-SLAM: Object Oriented SLAM with Deep Shape Priors","created":"2021-08-21","cited_by_count":30,"area":null},{"id":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29,"area":null},{"id":"2405.05792","title":"RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation","created":"2024-05-09","cited_by_count":25,"area":null},{"id":"2108.10165","title":"ODAM: Object Detection, Association, and Mapping using Posed RGB Video","created":"2021-08-23","cited_by_count":22,"area":null},{"id":"2109.09903","title":"AirDOS: Dynamic SLAM benefits from Articulated Objects","created":"2021-09-21","cited_by_count":21,"area":null},{"id":"2109.04884","title":"SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraints","created":"2021-09-10","cited_by_count":19,"area":null},{"id":"2203.13296","title":"RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers","created":"2022-03-24","cited_by_count":17,"area":null},{"id":"2209.08338","title":"OA-SLAM: Leveraging Objects for Camera Relocalization in Visual SLAM","created":"2022-09-17","cited_by_count":17,"area":null},{"id":"2305.07299","title":"An Object SLAM Framework for Association, Mapping, and High-Level Tasks","created":"2023-05-12","cited_by_count":15,"area":null},{"id":"2109.06479","title":"Large-scale Autonomous Flight with Real-time Semantic SLAM under Dense Forest Canopy","created":"2021-09-14","cited_by_count":12,"area":null},{"id":"2411.15043","title":"Open-Vocabulary Online Semantic Mapping for SLAM","created":"2024-11-22","cited_by_count":12,"area":null},{"id":"2312.05889","title":"SuperPrimitive: Scene Reconstruction at a Primitive Level","created":"2023-12-10","cited_by_count":11,"area":null},{"id":"2403.08125","title":"Q-SLAM: Quadric Representations for Monocular SLAM","created":"2024-03-12","cited_by_count":11,"area":null},{"id":"2107.11024","title":"A Deep Signed Directional Distance Function for Object Shape Representation","created":"2021-07-23","cited_by_count":10,"area":null},{"id":"2108.00355","title":"ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description","created":"2021-08-01","cited_by_count":10,"area":null},{"id":"2209.05629","title":"Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding","created":"2022-09-12","cited_by_count":10,"area":null},{"id":"2303.07308","title":"NeuSE: Neural SE(3)-Equivariant Embedding for Long-Term Object-Based Simultaneous Localization and Mapping","created":"2023-03-13","cited_by_count":10,"area":null},{"id":"2306.11739","title":"Multi-view 3D Object Reconstruction and Uncertainty Modelling with Neural Shape Prior","created":"2023-06-17","cited_by_count":9,"area":null},{"id":"2305.10029","title":"TextSLAM: Visual SLAM with Semantic Planar Text Features","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2309.15268","title":"ObVi-SLAM: Long-Term Object-Visual SLAM","created":"2023-09-26","cited_by_count":8,"area":null},{"id":"2402.06092","title":"CLIP-Loc: Multi-modal Landmark Association for Global Localization in Object-based Maps","created":"2024-02-08","cited_by_count":8,"area":null},{"id":"2504.14440","title":"SG-Reg: Generalizable and Efficient Scene Graph Registration","created":"2025-04-20","cited_by_count":8,"area":null},{"id":"2108.02522","title":"Object-Augmented RGB-D SLAM for Wide-Disparity Relocalisation","created":"2021-08-05","cited_by_count":7,"area":null},{"id":"2203.07662","title":"What's in the Black Box? The False Negative Mechanisms Inside Object Detectors","created":"2022-03-15","cited_by_count":7,"area":null},{"id":"2209.06428","title":"Semantic Visual Simultaneous Localization and Mapping: A Survey","created":"2022-09-14","cited_by_count":7,"area":null},{"id":"2303.15416","title":"3D Video Object Detection with Learnable Object-Centric Global Optimization","created":"2023-03-27","cited_by_count":7,"area":null},{"id":"2408.07917","title":"GOReloc: Graph-based Object-Level Relocalization for Visual SLAM","created":"2024-08-15","cited_by_count":7,"area":null},{"id":"2105.11494","title":"3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimation","created":"2021-05-24","cited_by_count":6,"area":null},{"id":"2209.14965","title":"DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment","created":"2022-09-29","cited_by_count":6,"area":null},{"id":"2402.13609","title":"VOOM: Robust Visual Object Odometry and Mapping using Hierarchical Landmarks","created":"2024-02-21","cited_by_count":6,"area":null},{"id":"2108.08957","title":"Unified Representation of Geometric Primitives for Graph-SLAM Optimization Using Decomposed Quadrics","created":"2021-08-20","cited_by_count":5,"area":null},{"id":"2109.07339","title":"S3LAM: Structured Scene SLAM","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2203.08040","title":"Simultaneous Localisation and Mapping with Quadric Surfaces","created":"2022-03-15","cited_by_count":5,"area":null},{"id":"2208.12513","title":"Perspective-1-Ellipsoid: Formulation, Analysis and Solutions of the Camera Pose Estimation Problem from One Ellipse-Ellipsoid Correspondence","created":"2022-08-26","cited_by_count":5,"area":null},{"id":"2203.04613","title":"Object-Based Visual Camera Pose Estimation From Ellipsoidal Model and 3D-Aware Ellipse Prediction","created":"2022-03-09","cited_by_count":4,"area":null},{"id":"2207.09445","title":"PoserNet: Refining Relative Camera Poses Exploiting Object Detections","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2203.03944","title":"An Online Semantic Mapping System for Extending and Enhancing Visual SLAM","created":"2022-03-08","cited_by_count":3,"area":null},{"id":"2207.07953","title":"Level Set-Based Camera Pose Estimation From Multiple 2D/3D Ellipse-Ellipsoid Correspondences","created":"2022-07-16","cited_by_count":3,"area":null},{"id":"2209.11894","title":"Closing the Loop: Graph Networks to Unify Semantic Objects and Visual Features for Multi-object Scenes","created":"2022-09-24","cited_by_count":3,"area":null},{"id":"2408.09191","title":"GSLAMOT: A Tracklet and Query Graph-based Simultaneous Locating, Mapping, and Multiple Object Tracking System","created":"2024-08-17","cited_by_count":3,"area":null},{"id":"2110.11491","title":"SymbioLCD: Ensemble-Based Loop Closure Detection using CNN-Extracted Objects and Visual Bag-of-Words","created":"2021-10-21","cited_by_count":2,"area":null},{"id":"2309.14211","title":"QuadricsNet: Learning Concise Representation for Geometric Primitives in Point Clouds","created":"2023-09-25","cited_by_count":2,"area":null},{"id":"2311.02831","title":"SemanticTopoLoop: Semantic Loop Closure With 3D Topological Graph Based on Quadric-Level Object Map","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2505.23756","title":"Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2109.09627","title":"Superquadric Object Representation for Optimization-based Semantic SLAM","created":"2021-09-20","cited_by_count":1,"area":null},{"id":"2110.08977","title":"Accurate and Robust Object-oriented SLAM with 3D Quadric Landmark Construction in Outdoor Environment","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2202.13855","title":"Large-Scale 3D Semantic Reconstruction for Automated Driving Vehicles with Adaptive Truncated Signed Distance Function","created":"2022-02-28","cited_by_count":1,"area":null},{"id":"2203.00567","title":"Descriptellation: Deep Learned Constellation Descriptors","created":"2022-03-01","cited_by_count":1,"area":null},{"id":"2209.07888","title":"TwistSLAM++: Fusing multiple modalities for accurate dynamic semantic SLAM","created":"2022-09-16","cited_by_count":1,"area":null},{"id":"2303.07872","title":"Object-based SLAM utilizing unambiguous pose parameters considering general symmetry types","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2309.17036","title":"UniQuadric: A SLAM Backend for Unknown Rigid Object 3D Tracking and Light-Weight Modeling","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2407.09718","title":"CLOVER: Context-aware Long-term Object Viewpoint- and Environment- Invariant Representation Learning","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2411.12620","title":"Maps from Motion (MfM): Generating 2D Semantic Maps from Sparse Multi-view Images","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2412.02998","title":"QuadricsReg: Large-Scale Point Cloud Registration using Quadric Primitives","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2506.15402","title":"MCOO-SLAM: A Multi-Camera Omnidirectional Object SLAM System","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2512.03522","title":"MSG-Loc: Multi-Label Likelihood-based Semantic Graph Matching for Object-Level Global Localization","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2602.06991","title":"LangGS-SLAM: Real-Time Language-Feature Gaussian Splatting SLAM","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2605.24111","title":"MASt3R-Nav: WayPixel Navigation in Relative 3D Maps","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2208.14738","title":"Scatter Points in Space: 3D Detection from Multi-view Monocular Images","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2211.02760","title":"Development and evaluation of automated localisation and reconstruction of all fruits on tomato plants in a greenhouse based on multi-view perception and 3D multi-object tracking","created":"2022-11-04","cited_by_count":0,"area":null},{"id":"2304.06373","title":"3DoF Localization from a Single Image and an Object Map: the Flatlandia Problem and Dataset","created":"2023-04-13","cited_by_count":0,"area":null},{"id":"2402.06951","title":"Semantic Object-level Modeling for Robust Visual Camera Relocalization","created":"2024-02-10","cited_by_count":0,"area":null},{"id":"2403.08586","title":"PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2405.01398","title":"Advancing Frontiers in SLAM: A Survey of Symbolic Representation and Human-Machine Teaming in Environmental Mapping","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2409.19459","title":"Language-guided Robust Navigation for Mobile Robots in Dynamically-changing Environments","created":"2024-09-28","cited_by_count":0,"area":null},{"id":"2503.01254","title":"Convex Hull-based Algebraic Constraint for Visual Quadric SLAM","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2503.02223","title":"DQO-MAP: Dual Quadrics Multi-Object mapping with Gaussian Splatting","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2505.22880","title":"Semantic Exploration and Dense Mapping of Complex Environments using Ground Robot with Panoramic LiDAR-Camera Fusion","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.08635","title":"SurfR: Surface Reconstruction with Multi-scale Attention","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2507.11653","title":"VISTA: Monocular Segmentation-Based Mapping for Appearance and View-Invariant Global Localization","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2605.02708","title":"Temporally Consistent Object 6D Pose Estimation for Robot Control","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.25953","title":"DSP-SLAM++: A Unified Framework for Multi-Class, High-Fidelity Object SLAM in the Wild","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.09455","title":"Hydra++: Real-Time Hierarchical 3D Scene Graph Construction With Object-Level Shape Estimation","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2609.04026","title":"Stable and Scalable Bundle Adjustment of Holistic 3D Structures","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.21804","title":"VideoReloc: Long-Term Indoor Video Relocalization against a Kilobyte-Scale Semantic Scene Graph","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}