{"total":144,"rows":[{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304,"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":"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":"2210.13641","title":"NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields","created":"2022-10-24","cited_by_count":188,"area":null},{"id":"2212.09802","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","created":"2022-12-19","cited_by_count":174,"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":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"id":"2207.09686","title":"Object-Compositional Neural Implicit Surfaces","created":"2022-07-20","cited_by_count":74,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2405.00915","title":"EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion","created":"2024-05-02","cited_by_count":67,"area":"diffusion"},{"id":"2207.05006","title":"TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs","created":"2022-07-11","cited_by_count":59,"area":null},{"id":"2503.10630","title":"UniGoal: Towards Universal Zero-shot Goal-oriented Navigation","created":"2025-03-13","cited_by_count":57,"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":"2305.16283","title":"CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion","created":"2023-05-25","cited_by_count":54,"area":"diffusion"},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","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":"2203.11937","title":"4D-OR: Semantic Scene Graphs for OR Domain Modeling","created":"2022-03-22","cited_by_count":49,"area":null},{"id":"2404.10220","title":"Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V","created":"2024-04-16","cited_by_count":40,"area":null},{"id":"2203.17251","title":"Continuous Scene Representations for Embodied AI","created":"2022-03-31","cited_by_count":39,"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":"2406.03175","title":"Dynamic 3D Gaussian Fields for Urban Areas","created":"2024-06-05","cited_by_count":35,"area":"wm"},{"id":"2309.15940","title":"Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphs","created":"2023-09-27","cited_by_count":33,"area":null},{"id":"2402.19302","title":"DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly","created":"2024-02-29","cited_by_count":33,"area":"diffusion"},{"id":"2404.03275","title":"DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2503.14029","title":"Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting","created":"2025-03-18","cited_by_count":31,"area":null},{"id":"2304.14880","title":"SGAligner : 3D Scene Alignment with Scene Graphs","created":"2023-04-28","cited_by_count":30,"area":null},{"id":"2304.06600","title":"Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation","created":"2023-04-13","cited_by_count":29,"area":null},{"id":"2404.00469","title":"SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs","created":"2024-03-30","cited_by_count":29,"area":null},{"id":"2212.11770","title":"S-Graphs+: Real-time Localization and Mapping leveraging Hierarchical Representations","created":"2022-12-22","cited_by_count":28,"area":null},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2404.00168","title":"Multi-Level Neural Scene Graphs for Dynamic Urban Environments","created":"2024-03-29","cited_by_count":27,"area":null},{"id":"2111.00312","title":"3DP3: 3D Scene Perception via Probabilistic Programming","created":"2021-10-30","cited_by_count":26,"area":null},{"id":"2202.10432","title":"Reasoning with Scene Graphs for Robot Planning under Partial Observability","created":"2022-02-21","cited_by_count":25,"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":"2503.07909","title":"FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction","created":"2025-03-10","cited_by_count":23,"area":null},{"id":"2109.09903","title":"AirDOS: Dynamic SLAM benefits from Articulated Objects","created":"2021-09-21","cited_by_count":21,"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":"2309.15702","title":"SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction","created":"2023-09-27","cited_by_count":21,"area":null},{"id":"2502.05874","title":"MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation","created":"2025-02-09","cited_by_count":19,"area":null},{"id":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19,"area":null},{"id":"2311.03783","title":"Scene-Driven Multimodal Knowledge Graph Construction for Embodied AI","created":"2023-11-07","cited_by_count":17,"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":"2410.10659","title":"PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion","created":"2024-10-14","cited_by_count":16,"area":null},{"id":"2412.01807","title":"Occam's LGS: An Efficient Approach for Language Gaussian Splatting","created":"2024-12-02","cited_by_count":16,"area":null},{"id":"2412.13652","title":"RelationField: Relate Anything in Radiance Fields","created":"2024-12-18","cited_by_count":16,"area":"mllm"},{"id":"2505.01458","title":"A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI","created":"2025-05-01","cited_by_count":16,"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":"2110.00273","title":"From SLAM to Situational Awareness: Challenges and Survey","created":"2021-10-01","cited_by_count":15,"area":null},{"id":"2404.12440","title":"Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds","created":"2024-04-18","cited_by_count":15,"area":null},{"id":"2105.07264","title":"Neural Trees for Learning on Graphs","created":"2021-05-15","cited_by_count":13,"area":null},{"id":"2511.10376","title":"MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation","created":"2025-11-13","cited_by_count":13,"area":null},{"id":"2109.12343","title":"Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems","created":"2021-09-25","cited_by_count":12,"area":null},{"id":"2409.15451","title":"Tag Map: A Text-Based Map for Spatial Reasoning and Navigation with Large Language Models","created":"2024-09-23","cited_by_count":12,"area":"lr"},{"id":"2502.15011","title":"CrossOver: 3D Scene Cross-Modal Alignment","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2602.16356","title":"Articulated 3D Scene Graphs for Open-World Mobile Manipulation","created":"2026-02-18","cited_by_count":11,"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":"2411.19162","title":"Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs","created":"2024-11-28","cited_by_count":10,"area":null},{"id":"2510.01049","title":"KeySG: Hierarchical Keyframe-Based 3D Scene Graphs","created":"2025-10-01","cited_by_count":10,"area":null},{"id":"2505.19510","title":"LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Study","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2608.11246","title":"Towards the Harness of Embodied Agents","created":"2026-08-03","cited_by_count":9,"area":"agents"},{"id":"2112.06180","title":"360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation","created":"2021-12-12","cited_by_count":8,"area":null},{"id":"2207.13738","title":"Break and Make: Interactive Structural Understanding Using LEGO Bricks","created":"2022-07-27","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":"2310.16737","title":"Translating Universal Scene Descriptions into Knowledge Graphs for Robotic Environment","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2106.15309","title":"Multimodal Semantic Scene Graphs for Holistic Modeling of Surgical Procedures","created":"2021-06-09","cited_by_count":6,"area":null},{"id":"2103.07356","title":"Hippocampal formation-inspired probabilistic generative model","created":"2021-03-12","cited_by_count":5,"area":null},{"id":"2502.18044","title":"S-Graphs 2.0 -- A Hierarchical-Semantic Optimization and Loop Closure for SLAM","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2505.06328","title":"A Grounded Memory System For Smart Personal Assistants","created":"2025-05-09","cited_by_count":5,"area":"agents"},{"id":"2505.09074","title":"Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectives","created":"2025-05-14","cited_by_count":5,"area":"wm"},{"id":"2509.24966","title":"Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2512.11903","title":"Aion: Towards Hierarchical 4D Scene Graphs with Temporal Flow Dynamics","created":"2025-12-10","cited_by_count":5,"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":"2210.12935","title":"360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning","created":"2022-10-24","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":"2310.00401","title":"Learning High-level Semantic-Relational Concepts for SLAM","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2409.10350","title":"Point2Graph: An End-to-end Point Cloud-based 3D Open-Vocabulary Scene Graph for Robot Navigation","created":"2024-09-16","cited_by_count":4,"area":null},{"id":"2503.09173","title":"Long-Term Planning Around Humans in Domestic Environments with 3D Scene Graphs","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2510.19255","title":"Advances in 4D Representation: Geometry, Motion, and Interaction","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2606.19383","title":"3D Scene Graphs: Open Challenges and Future Directions","created":"2026-06-15","cited_by_count":4,"area":null},{"id":"2109.06241","title":"Incremental Abstraction in Distributed Probabilistic SLAM Graphs","created":"2021-09-13","cited_by_count":3,"area":null},{"id":"2208.07109","title":"Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation","created":"2022-08-15","cited_by_count":3,"area":"moe"},{"id":"2212.01186","title":"A General Purpose Supervisory Signal for Embodied Agents","created":"2022-12-01","cited_by_count":3,"area":null},{"id":"2308.06719","title":"3D Scene Graph Prediction on Point Clouds Using Knowledge Graphs","created":"2023-08-13","cited_by_count":3,"area":null},{"id":"2409.11972","title":"Generation of Uncertainty-Aware High-Level Spatial Concepts in Factorized 3D Scene Graphs via Graph Neural Networks","created":"2024-09-18","cited_by_count":3,"area":null},{"id":"2606.08277","title":"Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees","created":"2026-06-06","cited_by_count":3,"area":null},{"id":"2211.08754","title":"Advanced Situational Graphs for Robot Navigation in Structured Indoor Environments","created":"2022-11-16","cited_by_count":2,"area":null},{"id":"2503.01783","title":"vS-Graphs: Tightly Coupling Visual SLAM and 3D Scene Graphs Exploiting Hierarchical Scene Understanding","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2507.12123","title":"Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2509.20401","title":"SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment","created":"2025-09-23","cited_by_count":2,"area":null},{"id":"2603.00409","title":"SSR: Pushing the Limit of Spatial Intelligence with Structured Scene Reasoning","created":"2026-02-28","cited_by_count":2,"area":"lr"},{"id":"2603.20239","title":"Rheos: Modelling Continuous Motion Dynamics in Hierarchical 3D Scene Graphs","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2606.05975","title":"T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2108.02957","title":"Smooth Mesh Estimation from Depth Data using Non-Smooth Convex Optimization","created":"2021-08-06","cited_by_count":1,"area":null},{"id":"2305.06820","title":"DeepSTEP -- Deep Learning-Based Spatio-Temporal End-To-End Perception for Autonomous Vehicles","created":"2023-05-11","cited_by_count":1,"area":"driving"},{"id":"2306.13760","title":"Task-Driven Graph Attention for Hierarchical Relational Object Navigation","created":"2023-06-23","cited_by_count":1,"area":null},{"id":"2412.05596","title":"TB-HSU: Hierarchical 3D Scene Understanding with Contextual Affordances","created":"2024-12-07","cited_by_count":1,"area":null},{"id":"2506.22593","title":"Pixels-to-Graph: Real-time Integration of Building Information Models and Scene Graphs for Semantic-Geometric Human-Robot Understanding","created":"2025-06-27","cited_by_count":1,"area":null}],"next_cursor":"100"}