{"total":173,"rows":[{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687,"area":null},{"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":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243,"area":null},{"id":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163,"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":"2505.12549","title":"VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold","created":"2025-05-18","cited_by_count":136,"area":null},{"id":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106,"area":null},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102,"area":null},{"id":"2402.03246","title":"SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM","created":"2024-02-05","cited_by_count":87,"area":null},{"id":"2208.11300","title":"E-NeRF: Neural Radiance Fields from a Moving Event Camera","created":"2022-08-24","cited_by_count":70,"area":null},{"id":"2207.09442","title":"Theseus: A Library for Differentiable Nonlinear Optimization","created":"2022-07-19","cited_by_count":65,"area":null},{"id":"2404.15259","title":"FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent","created":"2024-04-23","cited_by_count":61,"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":"2106.14386","title":"Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems","created":"2021-06-28","cited_by_count":54,"area":null},{"id":"2108.01176","title":"Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks","created":"2021-08-02","cited_by_count":52,"area":null},{"id":"2403.07494","title":"SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAM","created":"2024-03-12","cited_by_count":42,"area":null},{"id":"2308.14713","title":"R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras","created":"2023-08-28","cited_by_count":39,"area":null},{"id":"2210.03087","title":"Iterative Vision-and-Language Navigation","created":"2022-10-06","cited_by_count":35,"area":null},{"id":"2103.11470","title":"NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge","created":"2021-03-21","cited_by_count":32,"area":null},{"id":"2312.11713","title":"Indoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies","created":"2023-12-18","cited_by_count":25,"area":null},{"id":"2209.07896","title":"3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs","created":"2022-09-16","cited_by_count":24,"area":null},{"id":"2201.04114","title":"DM-VIO: Delayed Marginalization Visual-Inertial Odometry","created":"2022-01-11","cited_by_count":23,"area":null},{"id":"2202.12197","title":"Situational Graphs for Robot Navigation in Structured Indoor Environments","created":"2022-02-24","cited_by_count":21,"area":null},{"id":"2302.12772","title":"FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking Datasets","created":"2023-02-24","cited_by_count":21,"area":null},{"id":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19,"area":null},{"id":"2103.05041","title":"Advances in Inference and Representation for Simultaneous Localization and Mapping","created":"2021-03-08","cited_by_count":16,"area":null},{"id":"2107.08994","title":"CodeMapping: Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations","created":"2021-07-19","cited_by_count":16,"area":null},{"id":"2210.01276","title":"Probabilistic Volumetric Fusion for Dense Monocular SLAM","created":"2022-10-03","cited_by_count":16,"area":null},{"id":"2403.11496","title":"MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception","created":"2024-03-18","cited_by_count":16,"area":null},{"id":"2110.00273","title":"From SLAM to Situational Awareness: Challenges and Survey","created":"2021-10-01","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":"2309.09865","title":"Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight","created":"2023-09-18","cited_by_count":15,"area":null},{"id":"2311.01057","title":"Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO","created":"2023-11-02","cited_by_count":15,"area":null},{"id":"2409.12518","title":"Hier-SLAM: Scaling-up Semantics in SLAM with a Hierarchically Categorical Gaussian Splatting","created":"2024-09-19","cited_by_count":15,"area":null},{"id":"2303.08923","title":"Panoptic Mapping with Fruit Completion and Pose Estimation for Horticultural Robots","created":"2023-03-15","cited_by_count":14,"area":null},{"id":"2509.26639","title":"Benchmarking Egocentric Visual-Inertial SLAM at City Scale","created":"2025-09-30","cited_by_count":14,"area":null},{"id":"2108.05246","title":"A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation of Indoor Scenes","created":"2021-08-11","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":"2503.01646","title":"OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2209.04497","title":"General Place Recognition Survey: Towards the Real-world Autonomy Age","created":"2022-09-09","cited_by_count":11,"area":null},{"id":"2301.05206","title":"ImMesh: An Immediate LiDAR Localization and Meshing Framework","created":"2023-01-12","cited_by_count":11,"area":null},{"id":"2307.05999","title":"Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems","created":"2023-07-12","cited_by_count":11,"area":null},{"id":"2309.16818","title":"MEM: Multi-Modal Elevation Mapping for Robotics and Learning","created":"2023-09-28","cited_by_count":11,"area":null},{"id":"2309.17260","title":"PlaceNav: Topological Navigation through Place Recognition","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2310.16020","title":"ConvBKI: Real-Time Probabilistic Semantic Mapping Network with Quantifiable Uncertainty","created":"2023-10-24","cited_by_count":11,"area":null},{"id":"2412.01539","title":"The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs","created":"2024-12-02","cited_by_count":11,"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":"2204.13877","title":"Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM","created":"2022-04-29","cited_by_count":10,"area":null},{"id":"2505.23692","title":"Mobi-$\\pi$: Mobilizing Your Robot Learning Policy","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2106.11857","title":"HybVIO: Pushing the Limits of Real-time Visual-inertial Odometry","created":"2021-06-22","cited_by_count":8,"area":null},{"id":"2209.10663","title":"Convolutional Bayesian Kernel Inference for 3D Semantic Mapping","created":"2022-09-21","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":"2504.14440","title":"SG-Reg: Generalizable and Efficient Scene Graph Registration","created":"2025-04-20","cited_by_count":8,"area":null},{"id":"2204.10211","title":"SmartPortraits: Depth Powered Handheld Smartphone Dataset of Human Portraits for State Estimation, Reconstruction and Synthesis","created":"2022-04-21","cited_by_count":7,"area":null},{"id":"2207.01158","title":"VIP-SLAM: An Efficient Tightly-Coupled RGB-D Visual Inertial Planar SLAM","created":"2022-07-04","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":"2303.10962","title":"Neural Implicit Vision-Language Feature Fields","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2103.06182","title":"Dynamical Pose Estimation","created":"2021-03-10","cited_by_count":6,"area":null},{"id":"2105.04556","title":"TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2210.09739","title":"Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles with Label Propagation for Cross-Domain Adaptation","created":"2022-10-18","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":"2407.14279","title":"OpenSU3D: Open World 3D Scene Understanding using Foundation Models","created":"2024-07-19","cited_by_count":6,"area":null},{"id":"2506.01950","title":"DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2105.01595","title":"Self-Improving Semantic Perception for Indoor Localisation","created":"2021-05-04","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":"2312.01616","title":"SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System","created":"2023-12-04","cited_by_count":5,"area":null},{"id":"2501.01119","title":"Leverage Cross-Attention for End-to-End Open-Vocabulary Panoptic Reconstruction","created":"2025-01-02","cited_by_count":5,"area":null},{"id":"2503.17358","title":"Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2506.00225","title":"Understanding while Exploring: Semantics-driven Active Mapping","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2108.01654","title":"Comparison of modern open-source visual SLAM approaches","created":"2021-08-03","cited_by_count":4,"area":null},{"id":"2108.03180","title":"Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference","created":"2021-08-06","cited_by_count":4,"area":null},{"id":"2202.12384","title":"TwistSLAM: Constrained SLAM in Dynamic Environment","created":"2022-02-24","cited_by_count":4,"area":null},{"id":"2203.05332","title":"SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning","created":"2022-03-10","cited_by_count":4,"area":null},{"id":"2306.08648","title":"SimpleMapping: Real-Time Visual-Inertial Dense Mapping with Deep Multi-View Stereo","created":"2023-06-14","cited_by_count":4,"area":null},{"id":"2308.05515","title":"Mono-hydra: Real-time 3D scene graph construction from monocular camera input with IMU","created":"2023-08-10","cited_by_count":4,"area":null},{"id":"2411.07848","title":"Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation","created":"2024-11-12","cited_by_count":4,"area":null},{"id":"2103.10400","title":"RP-VIO: Robust Plane-based Visual-Inertial Odometry for Dynamic Environments","created":"2021-03-18","cited_by_count":3,"area":null},{"id":"2202.00765","title":"A Model for Multi-View Residual Covariances based on Perspective Deformation","created":"2022-02-01","cited_by_count":3,"area":null},{"id":"2211.00392","title":"Expansion of Visual Hints for Improved Generalization in Stereo Matching","created":"2022-11-01","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":"2409.07834","title":"Structured Pruning for Efficient Visual Place Recognition","created":"2024-09-12","cited_by_count":3,"area":null},{"id":"2410.04090","title":"High-Speed Stereo Visual SLAM for Low-Powered Computing Devices","created":"2024-10-05","cited_by_count":3,"area":null},{"id":"2412.11530","title":"RoMeO: Robust Metric Visual Odometry","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2501.00352","title":"PanoSLAM: Panoptic 3D Scene Reconstruction via Gaussian SLAM","created":"2024-12-31","cited_by_count":3,"area":null},{"id":"2503.04441","title":"EvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2511.16144","title":"LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2602.02974","title":"SceneLinker: Compositional 3D Scene Generation via Semantic Scene Graph from RGB Sequences","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2602.04517","title":"S-MUSt3R: Sliding Multi-view 3D Reconstruction","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2103.15967","title":"Detecting and Mapping Trees in Unstructured Environments with a Stereo Camera and Pseudo-Lidar","created":"2021-03-29","cited_by_count":2,"area":null},{"id":"2109.12131","title":"Automatic Map Update Using Dashcam Videos","created":"2021-09-24","cited_by_count":2,"area":null},{"id":"2208.02063","title":"Evaluation and comparison of eight popular Lidar and Visual SLAM algorithms","created":"2022-08-03","cited_by_count":2,"area":null},{"id":"2208.04274","title":"Visual-Inertial Multi-Instance Dynamic SLAM with Object-level Relocalisation","created":"2022-08-08","cited_by_count":2,"area":null},{"id":"2311.04107","title":"Interactive Semantic Map Representation for Skill-based Visual Object Navigation","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2311.16623","title":"Visual Semantic Navigation with Real Robots","created":"2023-11-28","cited_by_count":2,"area":null},{"id":"2404.11419","title":"SLAIM: Robust Dense Neural SLAM for Online Tracking and Mapping","created":"2024-04-17","cited_by_count":2,"area":null},{"id":"2410.15480","title":"Event-based Sensor Fusion and Application on Odometry: A Survey","created":"2024-10-20","cited_by_count":2,"area":null},{"id":"2412.00291","title":"Real-Time Metric-Semantic Mapping for Autonomous Navigation in Outdoor Environments","created":"2024-11-30","cited_by_count":2,"area":null},{"id":"2412.13726","title":"Unified Understanding of Environment, Task, and Human for Human-Robot Interaction in Real-World Environments","created":"2024-12-18","cited_by_count":2,"area":null},{"id":"2507.17594","title":"RemixFusion: Residual-based Mixed Representation for Large-scale Online RGB-D Reconstruction","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2508.13488","title":"ROVER: Robust Loop Closure Verification with Trajectory Prior in Repetitive Environments","created":"2025-08-19","cited_by_count":2,"area":null}],"next_cursor":"100"}