{"total":152,"rows":[{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592,"area":null},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559,"area":null},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204,"area":null},{"id":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169,"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":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147,"area":null},{"id":"2406.11824","title":"Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation","created":"2024-06-17","cited_by_count":137,"area":null},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133,"area":null},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110,"area":null},{"id":"2108.08841","title":"Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs","created":"2021-08-19","cited_by_count":84,"area":null},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"area":null},{"id":"2311.15383","title":"Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding","created":"2023-11-26","cited_by_count":64,"area":null},{"id":"2507.04047","title":"Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation","created":"2025-07-05","cited_by_count":51,"area":null},{"id":"2103.05558","title":"Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis","created":"2021-03-09","cited_by_count":49,"area":null},{"id":"2101.06605","title":"MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization","created":"2021-01-17","cited_by_count":46,"area":null},{"id":"2303.14408","title":"VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud","created":"2023-03-25","cited_by_count":43,"area":null},{"id":"2406.09401","title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations","created":"2024-06-13","cited_by_count":40,"area":null},{"id":"2408.11811","title":"EmbodiedSAM: Online Segment Any 3D Thing in Real Time","created":"2024-08-21","cited_by_count":40,"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":"2512.10863","title":"MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence","created":"2025-12-11","cited_by_count":38,"area":null},{"id":"2411.18894","title":"T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving","created":"2024-11-28","cited_by_count":35,"area":null},{"id":"2108.10743","title":"DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization","created":"2021-08-24","cited_by_count":33,"area":null},{"id":"2504.07958","title":"Detect Anything 3D in the Wild","created":"2025-04-10","cited_by_count":33,"area":null},{"id":"2212.06250","title":"ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes","created":"2022-12-12","cited_by_count":32,"area":null},{"id":"2409.18431","title":"Search3D: Hierarchical Open-Vocabulary 3D Segmentation","created":"2024-09-27","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":"2404.00469","title":"SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs","created":"2024-03-30","cited_by_count":29,"area":null},{"id":"2103.05368","title":"ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments","created":"2021-03-09","cited_by_count":28,"area":null},{"id":"2303.11048","title":"SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation","created":"2023-03-20","cited_by_count":27,"area":null},{"id":"2412.18450","title":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2209.12028","title":"Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline","created":"2022-09-24","cited_by_count":25,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"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":"2212.00786","title":"3D Segmentation of Humans in Point Clouds with Synthetic Data","created":"2022-12-01","cited_by_count":24,"area":null},{"id":"2503.22420","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","created":"2025-03-28","cited_by_count":23,"area":null},{"id":"2505.11383","title":"Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation","created":"2025-05-16","cited_by_count":23,"area":null},{"id":"2509.01106","title":"Robix: A Unified Model for Robot Interaction, Reasoning and Planning","created":"2025-09-01","cited_by_count":23,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2502.02548","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","created":"2025-02-04","cited_by_count":22,"area":null},{"id":"2308.12035","title":"RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D","created":"2023-08-23","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":"2409.04234","title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","created":"2024-09-06","cited_by_count":20,"area":null},{"id":"2509.10813","title":"InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts","created":"2025-09-13","cited_by_count":20,"area":null},{"id":"2203.08122","title":"From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2310.16494","title":"Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction","created":"2023-10-25","cited_by_count":19,"area":null},{"id":"2310.18773","title":"CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data","created":"2023-10-28","cited_by_count":18,"area":null},{"id":"2112.11691","title":"Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation","created":"2021-12-22","cited_by_count":17,"area":null},{"id":"2408.16662","title":"Space3D-Bench: Spatial 3D Question Answering Benchmark","created":"2024-08-29","cited_by_count":17,"area":null},{"id":"2111.14673","title":"3D Compositional Zero-shot Learning with DeCompositional Consensus","created":"2021-11-29","cited_by_count":16,"area":null},{"id":"2312.09138","title":"Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments","created":"2023-12-14","cited_by_count":15,"area":null},{"id":"2404.14565","title":"\"Where am I?\" Scene Retrieval with Language","created":"2024-04-22","cited_by_count":15,"area":null},{"id":"2503.10745","title":"Unifying 2D and 3D Vision-Language Understanding","created":"2025-03-13","cited_by_count":15,"area":null},{"id":"2506.08710","title":"SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting","created":"2025-06-10","cited_by_count":15,"area":null},{"id":"2208.09870","title":"Objects Can Move: 3D Change Detection by Geometric Transformation Constistency","created":"2022-08-21","cited_by_count":13,"area":null},{"id":"2502.15011","title":"CrossOver: 3D Scene Cross-Modal Alignment","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2505.04965","title":"DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding","created":"2025-05-08","cited_by_count":12,"area":null},{"id":"2502.00342","title":"Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering","created":"2025-02-01","cited_by_count":11,"area":null},{"id":"2305.13876","title":"Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans","created":"2023-05-23","cited_by_count":10,"area":null},{"id":"2403.19474","title":"SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2411.14869","title":"BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence","created":"2024-11-22","cited_by_count":10,"area":null},{"id":"2504.19500","title":"Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding","created":"2025-04-28","cited_by_count":10,"area":null},{"id":"2506.21117","title":"CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization","created":"2025-06-26","cited_by_count":10,"area":null},{"id":"2507.19993","title":"FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images","created":"2025-07-26","cited_by_count":10,"area":null},{"id":"2406.18387","title":"DoubleTake: Geometry Guided Depth Estimation","created":"2024-06-26","cited_by_count":9,"area":null},{"id":"2408.04034","title":"Task-oriented Sequential Grounding and Navigation in 3D Scenes","created":"2024-08-07","cited_by_count":9,"area":null},{"id":"2412.01398","title":"Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2501.16684","title":"SliceOcc: Indoor 3D Semantic Occupancy Prediction with Vertical Slice Representation","created":"2025-01-28","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":"2512.14364","title":"Unified Semantic Transformer for 3D Scene Understanding","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2604.05621","title":"FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos","created":"2026-04-07","cited_by_count":8,"area":null},{"id":"2503.17733","title":"GS-LTS: 3D Gaussian Splatting-Based Adaptive Modeling for Long-Term Service Robots","created":"2025-03-22","cited_by_count":7,"area":null},{"id":"2402.14215","title":"Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding","created":"2024-02-22","cited_by_count":6,"area":null},{"id":"2503.23024","title":"Empowering Large Language Models with 3D Situation Awareness","created":"2025-03-29","cited_by_count":6,"area":null},{"id":"2603.17605","title":"ReLaGS: Relational Language Gaussian Splatting","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2404.02527","title":"Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2502.19247","title":"ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2512.12622","title":"D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation","created":"2025-12-14","cited_by_count":5,"area":null},{"id":"2210.06240","title":"Explore Contextual Information for 3D Scene Graph Generation","created":"2022-10-12","cited_by_count":4,"area":null},{"id":"2312.01148","title":"Has Anything Changed? 3D Change Detection by 2D Segmentation Masks","created":"2023-12-02","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":"2503.15897","title":"Learning 3D Scene Analogies with Neural Contextual Scene Maps","created":"2025-03-20","cited_by_count":4,"area":null},{"id":"2506.04897","title":"From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2506.05199","title":"DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2510.04714","title":"Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2511.16567","title":"POMA-3D: The Point Map Way to 3D Scene Understanding","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2512.07599","title":"Online Segment Any 3D Thing as Instance Tracking","created":"2025-12-08","cited_by_count":4,"area":null},{"id":"2512.16908","title":"SceneDiff: A Benchmark and Method for Multiview Object Change Detection","created":"2025-12-18","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":"2207.08323","title":"PlaneSDF-based Change Detection for Long-term Dense Mapping","created":"2022-07-18","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":"2406.13302","title":"SituationalLLM: Proactive language models with scene awareness for dynamic, contextual task guidance","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2411.10509","title":"TESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene Understanding","created":"2024-11-15","cited_by_count":3,"area":null},{"id":"2504.09694","title":"Computer-Aided Layout Generation for Building Design: A Review","created":"2025-04-13","cited_by_count":3,"area":null},{"id":"2506.06909","title":"Gaussian Mapping for Evolving Scenes","created":"2025-06-07","cited_by_count":3,"area":null},{"id":"2512.20907","title":"PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding","created":"2025-12-24","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":"2604.10789","title":"ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2302.10425","title":"Instance-incremental Scene Graph Generation from Real-world Point Clouds via Normalizing Flows","created":"2023-02-21","cited_by_count":2,"area":null}],"next_cursor":"100"}