{"total":137,"rows":[{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94,"area":null},{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67,"area":"agents"},{"id":"2509.20414","title":"SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent","created":"2025-09-24","cited_by_count":56,"area":"agents"},{"id":"2602.10116","title":"SAGE: Scalable Agentic 3D Scene Generation for Embodied AI","created":"2026-02-10","cited_by_count":50,"area":"agents"},{"id":"2510.13802","title":"Trace Anything: Representing Any Video in 4D via Trajectory Fields","created":"2025-10-15","cited_by_count":33,"area":null},{"id":"2506.00742","title":"ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary","created":"2025-05-31","cited_by_count":28,"area":null},{"id":"2506.05341","title":"Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning","created":"2025-06-05","cited_by_count":28,"area":"lr"},{"id":"2510.22706","title":"IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction","created":"2025-10-26","cited_by_count":28,"area":null},{"id":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27,"area":null},{"id":"2503.14756","title":"SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis","created":"2025-03-18","cited_by_count":26,"area":null},{"id":"2503.04919","title":"FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement","created":"2025-03-06","cited_by_count":25,"area":"lr"},{"id":"2503.16848","title":"HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2512.11798","title":"Particulate: Feed-Forward 3D Object Articulation","created":"2025-12-12","cited_by_count":23,"area":null},{"id":"2412.14166","title":"MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data","created":"2024-12-18","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":"2503.13424","title":"Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation","created":"2025-03-17","cited_by_count":19,"area":null},{"id":"2508.14879","title":"MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds","created":"2025-08-20","cited_by_count":19,"area":null},{"id":"2511.16825","title":"WorldGen: From Text to Traversable and Interactive 3D Worlds","created":"2025-11-20","cited_by_count":19,"area":null},{"id":"2602.11757","title":"Code2Worlds: Empowering Coding LLMs for 4D World Generation","created":"2026-02-12","cited_by_count":19,"area":null},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2501.08983","title":"Compositional Generative Model of Unbounded 4D Cities","created":"2025-01-15","cited_by_count":17,"area":null},{"id":"2508.14461","title":"Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering","created":"2025-08-20","cited_by_count":16,"area":"diffusion"},{"id":"2508.16433","title":"HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction","created":"2025-08-22","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":"2509.14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation","created":"2025-09-18","cited_by_count":14,"area":null},{"id":"2507.07644","title":"FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations","created":"2025-07-10","cited_by_count":13,"area":"lr"},{"id":"2601.16982","title":"AnyView: Synthesizing Any Novel View in Dynamic Scenes","created":"2026-01-23","cited_by_count":12,"area":null},{"id":"2509.18631","title":"Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training","created":"2025-09-23","cited_by_count":10,"area":null},{"id":"2511.03589","title":"Human Mesh Modeling for Anny Body","created":"2025-11-05","cited_by_count":10,"area":null},{"id":"2604.02329","title":"Generative World Renderer","created":"2026-04-02","cited_by_count":10,"area":null},{"id":"2406.20077","title":"HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Model","created":"2024-06-28","cited_by_count":9,"area":"diffusion"},{"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":"2503.08008","title":"A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techniques, Datasets, and Future Research Prospects","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2506.22291","title":"RoomCraft: Controllable and Complete 3D Indoor Scene Generation","created":"2025-06-27","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":"2503.11633","title":"Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation","created":"2025-03-14","cited_by_count":8,"area":null},{"id":"2603.12193","title":"SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics","created":"2026-03-12","cited_by_count":8,"area":"vla"},{"id":"2608.05248","title":"WorldClaw: Agentic 3D Open-World Generation at Scale","created":"2026-08-05","cited_by_count":8,"area":"agents"},{"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":"2504.16930","title":"What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?","created":"2025-04-23","cited_by_count":7,"area":null},{"id":"2602.14968","title":"PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement","created":"2026-02-16","cited_by_count":7,"area":"agents"},{"id":"2603.11911","title":"InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model","created":"2026-03-12","cited_by_count":7,"area":"wm"},{"id":"2509.23728","title":"M3DLayout: A Multi-Source Dataset of 3D Indoor Layouts and Structured Descriptions for 3D Generation","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2510.10292","title":"From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2607.07459","title":"EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI","created":"2026-07-08","cited_by_count":6,"area":"agents"},{"id":"2601.05810","title":"SceneFoundry: Generating Interactive Infinite 3D Worlds","created":"2026-01-09","cited_by_count":5,"area":null},{"id":"2601.16272","title":"GR3EN: Generative Relighting for 3D Environments","created":"2026-01-22","cited_by_count":5,"area":"diffusion"},{"id":"2602.05362","title":"Imagine a City: CityGenAgent for Procedural 3D City Generation","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2505.10551","title":"Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data","created":"2025-05-15","cited_by_count":4,"area":"diffusion"},{"id":"2505.13466","title":"AgentSGEN: Multi-Agent LLM in the Loop for Semantic Collaboration and GENeration of Synthetic Data","created":"2025-05-07","cited_by_count":4,"area":"agents"},{"id":"2507.00981","title":"Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations","created":"2025-07-01","cited_by_count":4,"area":null},{"id":"2508.17832","title":"HLG: Comprehensive 3D Room Construction via Hierarchical Layout Generation","created":"2025-08-25","cited_by_count":4,"area":null},{"id":"2512.22351","title":"VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement","created":"2025-12-26","cited_by_count":4,"area":"mllm"},{"id":"2605.05207","title":"Syn4D: A Multiview Synthetic 4D Dataset","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2510.04536","title":"3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2510.16377","title":"Demeter: A Parametric Model of Crop Plant Morphology from the Real World","created":"2025-10-18","cited_by_count":3,"area":null},{"id":"2511.18005","title":"UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale","created":"2025-11-22","cited_by_count":3,"area":null},{"id":"2512.02340","title":"Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective","created":"2025-12-02","cited_by_count":3,"area":"lr"},{"id":"2603.24836","title":"WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2603.29089","title":"WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2605.12449","title":"LychSim: A Controllable and Interactive Simulation Framework for Vision Research","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2605.30161","title":"Why Far Looks Up: Probing Spatial Representation in Vision-Language Models","created":"2026-05-28","cited_by_count":3,"area":"lr"},{"id":"2504.15302","title":"RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU","created":"2025-04-17","cited_by_count":2,"area":"rag"},{"id":"2510.18189","title":"A Generalizable Light Transport 3D Embedding for Global Illumination","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2512.13597","title":"Lighting in Motion: Spatiotemporal HDR Lighting Estimation","created":"2025-12-15","cited_by_count":2,"area":"diffusion"},{"id":"2603.14790","title":"Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2603.27183","title":"Communicating about Space: Language-Mediated Spatial Integration Across Partial Views","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2604.04925","title":"SimpleProc: Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2604.19907","title":"SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation","created":"2026-04-21","cited_by_count":2,"area":"agents"},{"id":"2606.31680","title":"ShellMaker: Language-Guided Exterior Completion under Structural Constraints","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2607.19228","title":"IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2607.26646","title":"Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2608.18840","title":"Beyond Placement and Articulation: Usage-Driven Code Scenes for Embodied Interaction","created":"2026-08-19","cited_by_count":2,"area":null},{"id":"2505.20122","title":"MEBench: A Novel Benchmark for Understanding Mutual Exclusivity Bias in Vision-Language Models","created":"2025-05-26","cited_by_count":1,"area":"mllm"},{"id":"2506.21357","title":"CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2509.22864","title":"ControlEvents: Controllable Synthesis of Event Camera Datawith Foundational Prior from Image Diffusion Models","created":"2025-09-26","cited_by_count":1,"area":"diffusion"},{"id":"2509.24441","title":"NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.19814","title":"Toward A Better Understanding of Monocular Depth Evaluation","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2601.12234","title":"Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2603.28548","title":"Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow","created":"2026-03-30","cited_by_count":1,"area":"diffusion"},{"id":"2604.10512","title":"FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2604.11808","title":"Pair2Scene: Learning Local Object Relations for Procedural Scene Generation","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.16552","title":"Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.22828","title":"MetaEarth3D: Unlocking World-scale 3D Generation with Spatially Scalable Generative Modeling","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2604.26509","title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2605.26368","title":"Unified Panoramic Geometry Estimation via Multi-View Foundation Models","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.30819","title":"Function2Scene: 3D Indoor Scene Layout from Functional Specifications","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.01649","title":"PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.26738","title":"Do Image Editing Models Understand Lighting?","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2607.02301","title":"InvSplat: Inverse Feed-Forward Scene Splatting","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.28994","title":"Point2Radio: A Foundation Model for Cross-Scene Radio Fields from Material-Aware Point Clouds","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2608.12314","title":"StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2608.17975","title":"aDSL: Agentic 3D Creation via Joint Agent-Program Design","created":"2026-08-18","cited_by_count":1,"area":"agents"},{"id":"2608.24169","title":"ViSculpt: Visual-Centric Agentic Geometry Editing","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2609.01899","title":"TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.05927","title":"GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning","created":"2026-09-05","cited_by_count":1,"area":"agents"},{"id":"2609.36777","title":"Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2411.18644","title":"Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop","created":"2024-11-26","cited_by_count":0,"area":null}],"next_cursor":"100"}