{"total":72,"rows":[{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35,"area":null},{"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":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29,"area":null},{"id":"2510.22706","title":"IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction","created":"2025-10-26","cited_by_count":28,"area":null},{"id":"2511.19971","title":"VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction","created":"2025-11-25","cited_by_count":28,"area":null},{"id":"2601.17895","title":"Masked Depth Modeling for Spatial Perception","created":"2026-01-25","cited_by_count":28,"area":null},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2512.24766","title":"Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow","created":"2025-12-31","cited_by_count":25,"area":null},{"id":"2510.18873","title":"DSI-Bench: A Benchmark for Dynamic Spatial Intelligence","created":"2025-10-21","cited_by_count":23,"area":null},{"id":"2512.02015","title":"Generative Video Motion Editing with 3D Point Tracks","created":"2025-12-01","cited_by_count":23,"area":null},{"id":"2602.10094","title":"4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere","created":"2026-02-10","cited_by_count":22,"area":null},{"id":"2508.21060","title":"Multi-View 3D Point Tracking","created":"2025-08-28","cited_by_count":17,"area":null},{"id":"2509.17647","title":"VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video","created":"2025-09-22","cited_by_count":15,"area":null},{"id":"2601.14253","title":"Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis","created":"2026-01-20","cited_by_count":15,"area":null},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2606.19333","title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","created":"2026-06-17","cited_by_count":13,"area":null},{"id":"2512.20617","title":"SpatialTree: How Spatial Abilities Branch Out in MLLMs","created":"2025-12-23","cited_by_count":12,"area":null},{"id":"2510.08475","title":"DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos","created":"2025-10-09","cited_by_count":10,"area":null},{"id":"2511.04595","title":"UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction","created":"2025-11-06","cited_by_count":10,"area":null},{"id":"2512.18692","title":"EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images","created":"2025-12-21","cited_by_count":10,"area":null},{"id":"2604.03723","title":"SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation","created":"2026-04-04","cited_by_count":10,"area":null},{"id":"2602.14021","title":"Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow","created":"2026-02-15","cited_by_count":8,"area":null},{"id":"2602.22209","title":"WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videos","created":"2026-02-25","cited_by_count":8,"area":null},{"id":"2512.03350","title":"SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2605.30350","title":"DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation","created":"2026-05-28","cited_by_count":5,"area":null},{"id":"2606.18558","title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","created":"2026-06-17","cited_by_count":5,"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":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2512.04213","title":"Look Around and Pay Attention: Multi-camera Point Tracking Reimagined with Transformers","created":"2025-12-03","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":"2603.25791","title":"ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2603.22102","title":"FreeArtGS: Articulated Gaussian Splatting Under Free-moving Scenario","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2510.12777","title":"What If : Understanding Motion Through Sparse Interactions","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2512.05044","title":"Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2604.09366","title":"Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2605.22272","title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2606.17310","title":"SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues","created":"2026-06-15","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":"2511.16282","title":"Building temporally coherent 3D maps with VGGT for memory-efficient Semantic SLAM","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2512.06868","title":"Dynamic Visual SLAM using a General 3D Prior","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2602.08550","title":"GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2604.07990","title":"SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.19786","title":"Fast 4D Mesh Generation by Spatio-Temporal Attention Chains","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.08103","title":"Revisiting Articulated Parts Perception in Robot Manipulation","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2606.25344","title":"Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2606.26423","title":"CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.17790","title":"ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2609.01823","title":"Kirin: Animal Motion Generation from In-the-Wild Video","created":"2026-09-01","cited_by_count":1,"area":null},{"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":"2609.24487","title":"AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2511.22459","title":"Gaussians on Fire: High-Frequency Reconstruction of Flames","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2512.05398","title":"The Dynamic Prior: Understanding 3D Structures for Casual Dynamic Videos","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2512.10628","title":"K-Track: Kalman-Enhanced Tracking for Accelerating Deep Point Trackers on Edge Devices","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.20354","title":"3DSPA: A 3D Semantic Point Autoencoder for Evaluating Video Realism","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.17068","title":"TrackDeform3D: Markerless and Autonomous 3D Keypoint Tracking and Dataset Collection for Deformable Objects","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.21618","title":"4DGS360: 360{\\deg} Gaussian Reconstruction of Dynamic Objects from a Single Video","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.27300","title":"Complet4R: Geometric Complete 4D Reconstruction","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.08475","title":"LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.04527","title":"Velox: Learning Representations of 4D Geometry and Appearance","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.12027","title":"4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.16795","title":"3DPhysVideo: Consistency-Guided Flow SDE for Video Generation via 3D Scene Reconstruction and Physical Simulation","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.28813","title":"Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.27865","title":"Learning to Understand Body Language from Flight through Robust 3D Avatar Placing","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2607.29627","title":"FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.20748","title":"Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.25479","title":"4DStreamCtrl: Interactive Video Generation with Online 4D Control","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.05972","title":"Efficient and Robust Camera-independent Multiview 3D Geometric Reconstruction from Noisy Monocular Depth Estimation and Multiple Point Matching","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.19119","title":"Track, Articulate, Act: Generating Articulation from Casual Human Videos","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.02343","title":"SCOPE-4D: Endoscopic 4D Geometry Foundation Models","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.16591","title":"JtT: Rethinking Point Trajectory Diffusion for Diverse and Rigid Motion from an Image","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}