{"total":98,"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":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","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":"2207.09137","title":"ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild","created":"2022-07-19","cited_by_count":92,"area":null},{"id":"2405.18715","title":"NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild","created":"2024-05-29","cited_by_count":85,"area":null},{"id":"2106.15648","title":"Learning to Map for Active Semantic Goal Navigation","created":"2021-06-29","cited_by_count":50,"area":null},{"id":"2207.10606","title":"Approximate Differentiable Rendering with Algebraic Surfaces","created":"2022-07-21","cited_by_count":44,"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":"2509.05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","created":"2025-09-05","cited_by_count":35,"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":"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":"2409.09479","title":"MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry","created":"2024-09-14","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":"2103.16095","title":"Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments","created":"2021-03-30","cited_by_count":15,"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":"2312.05277","title":"3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection","created":"2023-12-08","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":"2103.11071","title":"Stereo CenterNet based 3D Object Detection for Autonomous Driving","created":"2021-03-20","cited_by_count":10,"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":"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":"2207.08794","title":"D$^3$FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance","created":"2022-07-18","cited_by_count":9,"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":"2210.02038","title":"MOTSLAM: MOT-assisted monocular dynamic SLAM using single-view depth estimation","created":"2022-10-05","cited_by_count":8,"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":"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":"2209.06376","title":"iSimLoc: Visual Global Localization for Previously Unseen Environments with Simulated Images","created":"2022-09-14","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":"2509.20757","title":"MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2105.00114","title":"Improved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames","created":"2021-04-30","cited_by_count":5,"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":"2304.06009","title":"Literature Review: Computer Vision Applications in Transportation Logistics and Warehousing","created":"2023-04-12","cited_by_count":5,"area":null},{"id":"2403.13714","title":"DBA-Fusion: Tightly Integrating Deep Dense Visual Bundle Adjustment with Multiple Sensors for Large-Scale Localization and Mapping","created":"2024-03-20","cited_by_count":5,"area":null},{"id":"2202.12384","title":"TwistSLAM: Constrained SLAM in Dynamic Environment","created":"2022-02-24","cited_by_count":4,"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":"2503.02955","title":"Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines","created":"2025-03-04","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":"2203.14550","title":"CenterLoc3D: Monocular 3D Vehicle Localization Network for Roadside Surveillance Cameras","created":"2022-03-28","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":"2210.06332","title":"ViewBirdiformer: Learning to recover ground-plane crowd trajectories and ego-motion from a single ego-centric view","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2406.13896","title":"SMORE: Simultaneous Map and Object REconstruction","created":"2024-06-19","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":"2101.10391","title":"Anytime 3D Object Reconstruction using Multi-modal Variational Autoencoder","created":"2021-01-25","cited_by_count":2,"area":null},{"id":"2101.10399","title":"Anchor Distance for 3D Multi-Object Distance Estimation from 2D Single Shot","created":"2021-01-25","cited_by_count":2,"area":null},{"id":"2309.07796","title":"For A More Comprehensive Evaluation of 6DoF Object Pose Tracking","created":"2023-09-14","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":"2609.05416","title":"WorldSculpt: Generating Compositional Worlds from Grounded Videos","created":"2026-09-04","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":"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":"2302.05192","title":"Virtually increasing the measurement frequency of LIDAR sensor utilizing a single RGB camera","created":"2023-02-10","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":"2304.05146","title":"Loop Closure Detection Based on Object-level Spatial Layout and Semantic Consistency","created":"2023-04-11","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":"2406.03835","title":"Monocular Localization with Semantics Map for Autonomous Vehicles","created":"2024-06-06","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":"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":"2509.17864","title":"ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos","created":"2025-09-22","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":"2605.13741","title":"LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.24767","title":"Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual Relocalization","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2104.07077","title":"Self-supervised Learning of 3D Object Understanding by Data Association and Landmark Estimation for Image Sequence","created":"2021-04-14","cited_by_count":0,"area":null},{"id":"2201.10602","title":"Jacobian Computation for Cumulative B-Splines on SE(3) and Application to Continuous-Time Object Tracking","created":"2022-01-25","cited_by_count":0,"area":null},{"id":"2303.02257","title":"Visual Perception System for Autonomous Driving","created":"2023-03-03","cited_by_count":0,"area":null},{"id":"2303.09800","title":"GOOD: General Optimization-based Fusion for 3D Object Detection via LiDAR-Camera Object Candidates","created":"2023-03-17","cited_by_count":0,"area":null},{"id":"2303.10959","title":"Constructing Metric-Semantic Maps using Floor Plan Priors for Long-Term Indoor Localization","created":"2023-03-20","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":"2407.19518","title":"Solving Short-Term Relocalization Problems In Monocular Keyframe Visual SLAM Using Spatial And Semantic Data","created":"2024-07-28","cited_by_count":0,"area":null},{"id":"2410.20969","title":"BEVPose: Unveiling Scene Semantics through Pose-Guided Multi-Modal BEV Alignment","created":"2024-10-28","cited_by_count":0,"area":null},{"id":"2411.19134","title":"Visual SLAMMOT Considering Multiple Motion Models","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2412.01500","title":"SF-Loc: A Visual Mapping and Geo-Localization System based on Sparse Visual Structure Frames","created":"2024-12-02","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":"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":"2610.08800","title":"A Review Of Robotic World Models For Dynamic Environments Based On Factor And Scene Graphs","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2610.16143","title":"All-St3R SLAM: Real-time RGB Dynamic SLAM with Pixel-wise Motion Masking","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}