{"total":151,"rows":[{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173,"area":null},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87,"area":null},{"id":"2510.15742","title":"Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset","created":"2025-10-17","cited_by_count":79,"area":null},{"id":"2512.07826","title":"OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing","created":"2025-12-08","cited_by_count":53,"area":null},{"id":"2508.10898","title":"Puppeteer: Rig and Animate Your 3D Models","created":"2025-08-14","cited_by_count":43,"area":null},{"id":"2507.10065","title":"MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second","created":"2025-07-14","cited_by_count":35,"area":null},{"id":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35,"area":null},{"id":"2601.15282","title":"Rethinking Video Generation Model for the Embodied World","created":"2026-01-21","cited_by_count":33,"area":null},{"id":"2506.01799","title":"WorldExplorer: Towards Generating Fully Navigable 3D Scenes","created":"2025-06-02","cited_by_count":26,"area":null},{"id":"2504.05692","title":"POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction","created":"2025-04-08","cited_by_count":25,"area":null},{"id":"2508.03694","title":"LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation","created":"2025-08-05","cited_by_count":22,"area":null},{"id":"2604.21915","title":"Vista4D: Video Reshooting with 4D Point Clouds","created":"2026-04-23","cited_by_count":18,"area":null},{"id":"2506.23361","title":"OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions","created":"2025-06-29","cited_by_count":17,"area":null},{"id":"2504.03198","title":"Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video","created":"2025-04-04","cited_by_count":16,"area":null},{"id":"2504.07093","title":"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution","created":"2025-04-09","cited_by_count":14,"area":null},{"id":"2507.08344","title":"MM-Gesture: Towards Precise Micro-Gesture Recognition through Multimodal Fusion","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2512.11988","title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","created":"2025-12-12","cited_by_count":14,"area":null},{"id":"2602.15828","title":"Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation","created":"2026-02-17","cited_by_count":14,"area":null},{"id":"2504.11092","title":"Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting","created":"2025-04-15","cited_by_count":11,"area":null},{"id":"2511.19827","title":"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding","created":"2025-11-25","cited_by_count":11,"area":null},{"id":"2511.18416","title":"4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2604.02329","title":"Generative World Renderer","created":"2026-04-02","cited_by_count":10,"area":null},{"id":"2606.28128","title":"PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation","created":"2026-06-26","cited_by_count":10,"area":null},{"id":"2602.01661","title":"From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2503.05549","title":"Stereo Any Video: Temporally Consistent Stereo Matching","created":"2025-03-07","cited_by_count":8,"area":null},{"id":"2504.17787","title":"The Fourth Monocular Depth Estimation Challenge","created":"2025-04-24","cited_by_count":8,"area":null},{"id":"2512.08269","title":"EgoX: Egocentric Video Generation from a Single Exocentric Video","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2502.03465","title":"Seeing World Dynamics in a Nutshell","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2506.01933","title":"E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2506.03150","title":"IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2512.22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation","created":"2025-12-28","cited_by_count":7,"area":null},{"id":"2510.01686","title":"FreeViS: Training-free Video Stylization with Inconsistent References","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2512.19629","title":"LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry","created":"2025-12-22","cited_by_count":6,"area":null},{"id":"2512.01677","title":"Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware Representation","created":"2025-12-01","cited_by_count":5,"area":null},{"id":"2603.24793","title":"AVControl: Efficient Framework for Training Audio-Visual Controls","created":"2026-03-25","cited_by_count":5,"area":null},{"id":"2512.03619","title":"LAMP: Language-Assisted Motion Planning for Controllable Video Generation","created":"2025-12-03","cited_by_count":4,"area":null},{"id":"2512.15635","title":"IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning","created":"2025-12-17","cited_by_count":4,"area":null},{"id":"2603.12250","title":"DVD: Deterministic Video Depth Estimation with Generative Priors","created":"2026-03-12","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":"2605.21431","title":"iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2607.24159","title":"DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning","created":"2026-07-27","cited_by_count":4,"area":null},{"id":"2608.15555","title":"RigidBench: Evaluating Rigid-Body Physics in Video Generation Models","created":"2026-08-16","cited_by_count":4,"area":null},{"id":"2511.12921","title":"Generative Photographic Control for Scene-Consistent Video Cinematic Editing","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2511.16993","title":"DepthFocus: Controllable Depth Estimation for See-Through Scenes","created":"2025-11-21","cited_by_count":3,"area":null},{"id":"2512.03040","title":"Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2512.09363","title":"StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation","created":"2025-12-10","cited_by_count":3,"area":null},{"id":"2512.10725","title":"Video Depth Propagation","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2602.14751","title":"Depth Completion as Parameter-Efficient Test-Time Adaptation","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2603.01765","title":"StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2603.03744","title":"DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2603.09668","title":"DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2605.23903","title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2605.25308","title":"Stabilizing Streaming Video Geometry via Dynamic Feature Normalization","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2605.30060","title":"Towards Consistent Video Geometry Estimation","created":"2026-05-28","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":"2610.03715","title":"4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes","created":"2026-10-02","cited_by_count":3,"area":null},{"id":"2506.15560","title":"RaCalNet: Radar Calibration Network for Sparse-Supervised Metric Depth Estimation","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2507.11540","title":"Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2509.17323","title":"DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Tracking","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2510.11107","title":"MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2512.08282","title":"PAVAS: Physics-Aware Video-to-Audio Synthesis","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2512.18159","title":"EndoStreamDepth: Temporally Consistent Monocular Depth Estimation for Endoscopic Video Streams","created":"2025-12-20","cited_by_count":2,"area":null},{"id":"2601.02793","title":"StableDPT: Temporal Stable Monocular Video Depth Estimation","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2601.03362","title":"Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2601.05246","title":"Pixel-Perfect Visual Geometry Estimation","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2603.03765","title":"LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2603.19048","title":"Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2606.19495","title":"LooseControlVideo: Directorial Video Control using Spatial Blocking","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2607.05355","title":"Faithfulness to Refusal: A Causal Audit of Neuron Selectors","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2609.05416","title":"WorldSculpt: Generating Compositional Worlds from Grounded Videos","created":"2026-09-04","cited_by_count":2,"area":null},{"id":"2508.12349","title":"EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2511.16262","title":"How Robot Dogs See the Unseeable: Improving Visual Interpretability via Peering for Exploratory Robots","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2512.02392","title":"From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2512.07596","title":"More than Segmentation: Benchmarking SAM 3 for Segmentation, 3D Perception, and Reconstruction in Robotic Surgery","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2512.13007","title":"Light Field Based 6DoF Tracking of Previously Unobserved Objects","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2601.16885","title":"GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.11154","title":"SurfPhase: 3D Interfacial Dynamics in Two-Phase Flows from Sparse Videos","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.12064","title":"Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.29092","title":"TrajectoryMover: Generative Movement of Object Trajectories in Videos","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2603.29296","title":"MotionScale: Reconstructing Appearance, Geometry, and Motion of Dynamic Scenes with Scalable 4D Gaussian Splatting","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.09352","title":"LuMon: A Comprehensive Benchmark and Development Suite with Novel Datasets for Lunar Monocular Depth Estimation","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.24718","title":"WildLIFT: Lifting monocular drone video to 3D for species-agnostic wildlife monitoring","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2605.10523","title":"Improving Human Image Animation via Semantic Representation Alignment","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.12774","title":"WildPose: A Unified Framework for Robust Pose Estimation in the Wild","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.03490","title":"TrAction: Action Recognition with Sparse Trajectories","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.03540","title":"Attend to Anything: Foundation Model for Unified Human Attention Modeling","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.13497","title":"SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.20891","title":"Go-with-the-Track: Video Compositing and Motion Control with Point Tracking","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2607.08771","title":"ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2607.08772","title":"Wat3R: Underwater 3D Geometry Learning without Annotations","created":"2026-07-09","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":"2607.28394","title":"Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.12179","title":"Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2503.07739","title":"SIRE: SE(3) Intrinsic Rigidity Embeddings","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2503.09160","title":"WonderVerse: Extendable 3D Scene Generation with Video Generative Models","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2509.05728","title":"LiDAR-BIND-T: Improved and Temporally Consistent Sensor Modality Translation and Fusion for Robotic Applications","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2510.06216","title":"Dropping the D: RGB-D SLAM Without the Depth Sensor","created":"2025-10-07","cited_by_count":0,"area":null}],"next_cursor":"100"}