{"total":181,"rows":[{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315,"area":"lr"},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287,"area":null},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277,"area":null},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250,"area":null},{"id":"2501.03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","created":"2025-01-07","cited_by_count":185,"area":"diffusion"},{"id":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179,"area":null},{"id":"2409.18124","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","created":"2024-09-26","cited_by_count":166,"area":"diffusion"},{"id":"2504.13152","title":"St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World","created":"2025-04-17","cited_by_count":89,"area":null},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87,"area":null},{"id":"2601.03782","title":"PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation","created":"2026-01-07","cited_by_count":82,"area":"wm"},{"id":"2412.03079","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","created":"2024-12-04","cited_by_count":79,"area":null},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76,"area":null},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74,"area":null},{"id":"2407.05921","title":"TAPVid-3D: A Benchmark for Tracking Any Point in 3D","created":"2024-07-08","cited_by_count":72,"area":null},{"id":"2504.14717","title":"TAPIP3D: Tracking Any Point in Persistent 3D Geometry","created":"2025-04-20","cited_by_count":69,"area":null},{"id":"2504.07961","title":"Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction","created":"2025-04-10","cited_by_count":67,"area":"diffusion"},{"id":"2410.24211","title":"DELTA: Dense Efficient Long-range 3D Tracking for any video","created":"2024-10-31","cited_by_count":65,"area":null},{"id":"2506.07310","title":"AllTracker: Efficient Dense Point Tracking at High Resolution","created":"2025-06-08","cited_by_count":58,"area":null},{"id":"2512.08924","title":"Efficiently Reconstructing Dynamic Scenes One D4RT at a Time","created":"2025-12-09","cited_by_count":54,"area":null},{"id":"2412.06016","title":"Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation","created":"2024-12-08","cited_by_count":44,"area":"diffusion"},{"id":"2503.16318","title":"Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction","created":"2025-03-20","cited_by_count":44,"area":null},{"id":"2410.18912","title":"Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling","created":"2024-10-24","cited_by_count":43,"area":null},{"id":"2506.23135","title":"RoboScape: Physics-informed Embodied World Model","created":"2025-06-29","cited_by_count":40,"area":"wm"},{"id":"2411.06525","title":"I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength","created":"2024-11-10","cited_by_count":39,"area":null},{"id":"2501.02690","title":"GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking","created":"2025-01-05","cited_by_count":39,"area":null},{"id":"2504.01016","title":"GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors","created":"2025-04-01","cited_by_count":37,"area":"diffusion"},{"id":"2504.05579","title":"TAPNext: Tracking Any Point (TAP) as Next Token Prediction","created":"2025-04-08","cited_by_count":37,"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":"2510.13802","title":"Trace Anything: Representing Any Video in 4D via Trajectory Fields","created":"2025-10-15","cited_by_count":33,"area":null},{"id":"2406.13870","title":"Splatter a Video: Video Gaussian Representation for Versatile Processing","created":"2024-06-19","cited_by_count":31,"area":null},{"id":"2411.16877","title":"PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence","created":"2024-11-25","cited_by_count":28,"area":null},{"id":"2502.13142","title":"Pre-training Auto-regressive Robotic Models with 4D Representations","created":"2025-02-18","cited_by_count":27,"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":"2504.14516","title":"Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction","created":"2025-04-20","cited_by_count":24,"area":null},{"id":"2501.05020","title":"Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation","created":"2025-01-09","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":"2501.10357","title":"Zero-Shot Monocular Scene Flow Estimation in the Wild","created":"2025-01-17","cited_by_count":22,"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":"2602.10094","title":"4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere","created":"2026-02-10","cited_by_count":22,"area":null},{"id":"2409.02104","title":"DynOMo: Online Point Tracking by Dynamic Online Monocular Gaussian Reconstruction","created":"2024-09-03","cited_by_count":20,"area":null},{"id":"2411.17765","title":"I2VControl: Disentangled and Unified Video Motion Synthesis Control","created":"2024-11-26","cited_by_count":20,"area":null},{"id":"2407.16291","title":"TAPTRv2: Attention-based Position Update Improves Tracking Any Point","created":"2024-07-23","cited_by_count":18,"area":null},{"id":"2412.07721","title":"ObjCtrl-2.5D: Training-free Object Control with Camera Poses","created":"2024-12-10","cited_by_count":18,"area":null},{"id":"2506.14198","title":"AMPLIFY: Actionless Motion Priors for Robot Learning from Videos","created":"2025-06-17","cited_by_count":18,"area":"wm"},{"id":"2505.10075","title":"FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation","created":"2025-05-15","cited_by_count":17,"area":"wm"},{"id":"2508.21060","title":"Multi-View 3D Point Tracking","created":"2025-08-28","cited_by_count":17,"area":null},{"id":"2412.05848","title":"MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation","created":"2024-12-08","cited_by_count":16,"area":"diffusion"},{"id":"2506.09997","title":"DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos","created":"2025-06-11","cited_by_count":15,"area":null},{"id":"2404.07097","title":"Fast Encoder-Based 3D from Casual Videos via Point Track Processing","created":"2024-04-10","cited_by_count":14,"area":null},{"id":"2506.04227","title":"Object-centric 3D Motion Field for Robot Learning from Human Videos","created":"2025-06-04","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":"2504.14687","title":"Seurat: From Moving Points to Depth","created":"2025-04-20","cited_by_count":13,"area":null},{"id":"2603.02573","title":"Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels","created":"2026-03-03","cited_by_count":13,"area":null},{"id":"2501.14945","title":"MATCHA:Towards Matching Anything","created":"2025-01-24","cited_by_count":12,"area":null},{"id":"2502.13078","title":"L4P: Towards Unified Low-Level 4D Vision Perception","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2505.10566","title":"3D-Fixup: Advancing Photo Editing with 3D Priors","created":"2025-05-15","cited_by_count":12,"area":"diffusion"},{"id":"2506.08004","title":"Dynamic View Synthesis as an Inverse Problem","created":"2025-06-09","cited_by_count":12,"area":"diffusion"},{"id":"2512.20617","title":"SpatialTree: How Spatial Abilities Branch Out in MLLMs","created":"2025-12-23","cited_by_count":12,"area":null},{"id":"2506.03605","title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2509.21986","title":"Developing Vision-Language-Action Model from Egocentric Videos","created":"2025-09-26","cited_by_count":11,"area":"vla"},{"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":"2407.18249","title":"Trajectory-aligned Space-time Tokens for Few-shot Action Recognition","created":"2024-07-25","cited_by_count":10,"area":null},{"id":"2411.19162","title":"Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs","created":"2024-11-28","cited_by_count":10,"area":null},{"id":"2508.01170","title":"DELTAv2: Accelerating Dense 3D Tracking","created":"2025-08-02","cited_by_count":10,"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":"2604.04911","title":"SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing","created":"2026-04-06","cited_by_count":10,"area":null},{"id":"2412.21079","title":"Edicho: Consistent Image Editing in the Wild","created":"2024-12-30","cited_by_count":9,"area":null},{"id":"2509.18676","title":"3D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D Space","created":"2025-09-23","cited_by_count":9,"area":"diffusion"},{"id":"2512.13604","title":"LongVie 2: Multimodal Controllable Ultra-Long Video World Model","created":"2025-12-15","cited_by_count":9,"area":"wm"},{"id":"2601.22301","title":"Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes","created":"2026-01-29","cited_by_count":9,"area":null},{"id":"2411.18671","title":"TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video","created":"2024-11-27","cited_by_count":8,"area":null},{"id":"2502.03639","title":"Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach","created":"2025-02-05","cited_by_count":8,"area":"diffusion"},{"id":"2509.23492","title":"Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos","created":"2025-09-27","cited_by_count":8,"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":"2604.05621","title":"FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos","created":"2026-04-07","cited_by_count":8,"area":null},{"id":"2411.09551","title":"MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation","created":"2024-11-14","cited_by_count":7,"area":null},{"id":"2503.18950","title":"Target-Aware Video Diffusion Models","created":"2025-03-24","cited_by_count":7,"area":"diffusion"},{"id":"2504.01872","title":"CoMatcher: Multi-View Collaborative Feature Matching","created":"2025-04-02","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":"2508.03695","title":"Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition","created":"2025-08-05","cited_by_count":7,"area":null},{"id":"2512.08358","title":"TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels","created":"2025-12-09","cited_by_count":7,"area":null},{"id":"2602.06959","title":"CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation","created":"2026-02-06","cited_by_count":7,"area":null},{"id":"2604.03305","title":"HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis","created":"2026-03-31","cited_by_count":7,"area":null},{"id":"2409.04243","title":"Hybrid Cost Volume for Memory-Efficient Optical Flow","created":"2024-09-06","cited_by_count":6,"area":null},{"id":"2506.08220","title":"Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2506.08894","title":"Product of Experts for Visual Generation","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2510.08527","title":"FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2512.11356","title":"Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video","created":"2025-12-12","cited_by_count":6,"area":null},{"id":"2412.07696","title":"SimVS: Simulating World Inconsistencies for Robust View Synthesis","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2509.07472","title":"ANYPORTAL: Zero-Shot Consistent Video Background Replacement","created":"2025-09-09","cited_by_count":5,"area":"diffusion"},{"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":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2605.12587","title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","created":"2026-05-12","cited_by_count":5,"area":"diffusion"},{"id":"2607.22534","title":"SM4RT: Learning Structured Motion Geometry for 4D Reconstruction","created":"2026-07-24","cited_by_count":5,"area":null},{"id":"2410.19996","title":"A-MFST: Adaptive Multi-Flow Sparse Tracker for Real-Time Tissue Tracking Under Occlusion","created":"2024-10-25","cited_by_count":4,"area":null},{"id":"2512.02006","title":"MV-TAP: Tracking Any Point in Multi-View Videos","created":"2025-12-01","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":"2512.10940","title":"OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis","created":"2025-12-11","cited_by_count":4,"area":"diffusion"}],"next_cursor":"100"}