{"total":96,"rows":[{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314,"area":null},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2412.06974","title":"MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds","created":"2024-12-09","cited_by_count":141,"area":null},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110,"area":null},{"id":"2412.09401","title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","created":"2024-12-12","cited_by_count":102,"area":null},{"id":"2412.02193","title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models","created":"2024-12-03","cited_by_count":96,"area":"lr"},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"area":null},{"id":"2510.23607","title":"Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations","created":"2025-10-27","cited_by_count":45,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35,"area":null},{"id":"2503.18944","title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","created":"2025-03-24","cited_by_count":31,"area":null},{"id":"2512.16561","title":"N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models","created":"2025-12-18","cited_by_count":29,"area":"lr"},{"id":"2410.08208","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2601.11514","title":"ShapeR: Robust Conditional 3D Shape Generation from Casual Captures","created":"2026-01-16","cited_by_count":22,"area":null},{"id":"2507.02861","title":"LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans","created":"2025-07-03","cited_by_count":21,"area":null},{"id":"2506.21348","title":"PanSt3R: Multi-view Consistent Panoptic Segmentation","created":"2025-06-26","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":"2602.23361","title":"VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale","created":"2026-02-26","cited_by_count":18,"area":null},{"id":"2509.01584","title":"ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association","created":"2025-09-01","cited_by_count":16,"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":"2606.01057","title":"3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code","created":"2026-05-31","cited_by_count":15,"area":"agents"},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2604.04931","title":"LoMa: Local Feature Matching Revisited","created":"2026-04-06","cited_by_count":11,"area":null},{"id":"2507.22052","title":"Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos","created":"2025-07-29","cited_by_count":10,"area":null},{"id":"2502.04223","title":"\\'Eclair -- Extracting Content and Layout with Integrated Reading Order for Documents","created":"2025-02-06","cited_by_count":9,"area":null},{"id":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2601.15283","title":"LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes","created":"2026-01-21","cited_by_count":9,"area":null},{"id":"2411.18807","title":"Reconstructing Animals and the Wild","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2412.15200","title":"DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation","created":"2024-12-19","cited_by_count":7,"area":null},{"id":"2603.05591","title":"Thinking with Spatial Code for Physical-World Video Reasoning","created":"2026-03-05","cited_by_count":7,"area":"lr"},{"id":"2604.05212","title":"Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D","created":"2026-04-06","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2503.02745","title":"ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points","created":"2025-03-04","cited_by_count":6,"area":null},{"id":"2506.02459","title":"ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2603.07660","title":"Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence","created":"2026-03-08","cited_by_count":6,"area":null},{"id":"2605.30215","title":"D\\'ej\\`a View: Looping Transformers for Multi-View 3D Reconstruction","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2603.08592","title":"Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations","created":"2026-03-09","cited_by_count":5,"area":"lr"},{"id":"2603.26661","title":"GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation","created":"2026-03-27","cited_by_count":5,"area":"diffusion"},{"id":"2604.22984","title":"BrickNet: Graph-Backed Generative Brick Assembly","created":"2026-04-24","cited_by_count":5,"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":"2506.08002","title":"Aligning Text, Images, and 3D Structure Token-by-Token","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2601.08831","title":"3AM: 3egment Anything with Geometric Consistency in Videos","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2602.04439","title":"TrajVG: 3D Trajectory-Coupled Visual Geometry Learning","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2605.07342","title":"Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate","created":"2026-05-08","cited_by_count":4,"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":"2503.08208","title":"Explaining Human Preferences via Metrics for Structured 3D Reconstruction","created":"2025-03-11","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":"2603.18496","title":"NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Data","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2607.01015","title":"SuperFlex: Deformable Superquadrics for Point Cloud Decomposition","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2607.12993","title":"X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras","created":"2026-07-14","cited_by_count":3,"area":null},{"id":"2609.08848","title":"FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2602.22716","title":"SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs","created":"2026-02-26","cited_by_count":2,"area":"mllm"},{"id":"2602.23224","title":"UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2605.12586","title":"3D Primitives are a Spatial Language for VLMs","created":"2026-05-12","cited_by_count":2,"area":"mllm"},{"id":"2605.30561","title":"VLM3: Vision Language Models Are Native 3D Learners","created":"2026-05-28","cited_by_count":2,"area":"mllm"},{"id":"2607.08537","title":"Whareformer: Learning to Track What is Where in Long Egocentric Videos","created":"2026-07-09","cited_by_count":2,"area":null},{"id":"2411.17467","title":"Semantic-Free Procedural 3D Shapes Are Surprisingly Good Teachers","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2501.17044","title":"Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformers","created":"2025-01-28","cited_by_count":1,"area":null},{"id":"2508.07769","title":"Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation","created":"2025-08-11","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":"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":"2601.04204","title":"TeachMaster: Generative Teaching via Code","created":"2025-12-07","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":"2604.11809","title":"Who Handles Orientation? Investigating Invariance in Feature Matching","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.14315","title":"TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.18214","title":"EgoInteract: Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2608.27529","title":"Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.15018","title":"G-ray: Ray-Level Relative Geometric Position Encoding in Multi-View Vision Transformers under Camera Heterogeneity","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2609.24487","title":"AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2412.05771","title":"Prism: Semi-Supervised Multi-View Stereo with Monocular Structure Priors","created":"2024-12-08","cited_by_count":0,"area":null},{"id":"2506.19639","title":"HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2509.24236","title":"PROFusion: Robust and Accurate Dense Reconstruction via Camera Pose Regression and Optimization","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2511.18814","title":"DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2511.18817","title":"Disc3D: Automatic Curation of High-Quality 3D Dialog Data via Discriminative Object Referring","created":"2025-11-24","cited_by_count":0,"area":"mllm"},{"id":"2603.16016","title":"FlatLands: Generative Floormap Completion From a Single Egocentric View","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.29733","title":"Leveraging Synthetic Data for Enhancing Egocentric Hand-Object Interaction Detection","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.01907","title":"Lifting Unlabeled Internet-level Data for 3D Scene Understanding","created":"2026-04-02","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":"2606.03287","title":"BA-T: An Iterative Transformer for Two-View Bundle Adjustment","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.02908","title":"Holo-Captioning: Toward the Text Equivalent of 3D Scenes","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.03614","title":"IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2607.15211","title":"MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos","created":"2026-07-16","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":"2608.07547","title":"Learning an Interior Layout Policy in a Domain Specific Language Action Space","created":"2026-07-31","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":"2608.30751","title":"Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.02359","title":"TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.09507","title":"RoMa-$\\Omega$: What Feed-Forward 3D Models Know About Image Matching","created":"2026-09-08","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":"2609.23796","title":"Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.31595","title":"GraphWrit3R: End-to-End 3D Scene Graph Writing","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.01314","title":"ARROW: Arbitrary Reconstruction and Tracking of 4D Observations in the Wild","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01863","title":"LiteReality-Agent: An Agentic System for Interactable 3D Indoor Scene Reconstruction","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"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}