{"total":45,"rows":[{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289,"area":null},{"id":"2403.13064","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","created":"2024-03-19","cited_by_count":96,"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":"2406.15658","title":"TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning","created":"2024-06-21","cited_by_count":31,"area":null},{"id":"2408.16325","title":"P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoising","created":"2024-08-29","cited_by_count":18,"area":null},{"id":"2311.12174","title":"LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories","created":"2023-11-20","cited_by_count":14,"area":null},{"id":"2407.10439","title":"PolyRoom: Room-aware Transformer for Floorplan Reconstruction","created":"2024-07-15","cited_by_count":9,"area":null},{"id":"2407.12267","title":"Generating 3D House Wireframes with Semantics","created":"2024-07-17","cited_by_count":8,"area":null},{"id":"2509.11301","title":"UnLoc: Leveraging Depth Uncertainties for Floorplan Localization","created":"2025-09-14","cited_by_count":8,"area":null},{"id":"2406.09160","title":"Beyond the Frontier: Predicting Unseen Walls from Occupancy Grids by Learning from Floor Plans","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2311.18068","title":"ALSTER: A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction","created":"2023-11-29","cited_by_count":6,"area":null},{"id":"2407.10687","title":"FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2407.14920","title":"RoIPoly: Vectorized Building Outline Extraction Using Vertex and Logit Embeddings","created":"2024-07-20","cited_by_count":6,"area":null},{"id":"2404.06442","title":"QueSTMaps: Queryable Semantic Topological Maps for 3D Scene Understanding","created":"2024-04-09","cited_by_count":5,"area":null},{"id":"2412.00955","title":"WAFFLE: Multimodal Floorplan Understanding in the Wild","created":"2024-12-01","cited_by_count":5,"area":null},{"id":"2506.09369","title":"ScaleLSD: Scalable Deep Line Segment Detection Streamlined","created":"2025-06-11","cited_by_count":5,"area":null},{"id":"2602.06507","title":"FloorplanVLM: A Vision-Language Model for Floorplan Vectorization","created":"2026-02-06","cited_by_count":5,"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":"2503.11806","title":"Human-in-the-Loop Local Corrections of 3D Scene Layouts via Infilling","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2404.09993","title":"No More Ambiguity in 360{\\deg} Room Layout via Bi-Layout Estimation","created":"2024-04-15","cited_by_count":3,"area":null},{"id":"2502.16779","title":"Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2509.15459","title":"CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2403.08721","title":"Historical Astronomical Diagrams Decomposition in Geometric Primitives","created":"2024-03-13","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":"2508.04659","title":"PixCuboid: Room Layout Estimation from Multi-view Featuremetric Alignment","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2509.15750","title":"FloorSAM: SAM-Guided Floorplan Reconstruction with Semantic-Geometric Fusion","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2509.21388","title":"TUN3D: Towards Real-World Scene Understanding from Unposed Images","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2510.13234","title":"UniVector: Unified Vector Extraction via Instance-Geometry Interaction","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2511.16521","title":"YOWO: You Only Walk Once to Jointly Map An Indoor Scene and Register Ceiling-mounted Cameras","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2512.02450","title":"HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2512.05597","title":"Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2602.09016","title":"Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2605.22581","title":"SceneAligner: 3D-Grounded Floorplan Localization in the Wild","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2608.07012","title":"Scenix: Sparse-View 3D Scene Reconstruction via Executable Scene Programs","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2410.05530","title":"VisDiff: SDF-Guided Polygon Generation for Visibility Reconstruction and Recognition","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2503.00397","title":"Floorplan-SLAM: A Real-Time, High-Accuracy, and Long-Term Multi-Session Point-Plane SLAM for Efficient Floorplan Reconstruction","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2503.23105","title":"Open-Vocabulary Semantic Segmentation with Uncertainty Alignment for Robotic Scene Understanding in Indoor Building Environments","created":"2025-03-29","cited_by_count":0,"area":null},{"id":"2605.16832","title":"Coarse Semantic Injection for LLM-Conditioned Structured Indoor Prediction","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.20946","title":"Scaling Diverse Language Generation for 3D Visual Grounding","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.10822","title":"Graph Neural Networks for RFID-Based Spatial Geometry Inference in Spatial AI Systems","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.03323","title":"PolyLayout: Multi-room Manhattan Layout Estimation","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.21447","title":"BIMScript: Material-Aware Structured Scene Programs for BIM Ingestion","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.25608","title":"When Should a Network Emit Geometry, and When Should It Detect It? Readout, Reconciliation, and Representation in Floorplan Vectorization","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.12723","title":"Multimodal Floorplan Encoding: Learning Dense Modality-Invariant Representations","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.14315","title":"MvFFN: Multi-view Floor plan Feed-forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}