{"total":79,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580,"area":null},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548,"area":null},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442,"area":null},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367,"area":null},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319,"area":null},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228,"area":null},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194,"area":null},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193,"area":null},{"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":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"area":null},{"id":"2303.13791","title":"Progressively Optimized Local Radiance Fields for Robust View Synthesis","created":"2023-03-24","cited_by_count":103,"area":null},{"id":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91,"area":null},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87,"area":null},{"id":"2405.18715","title":"NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild","created":"2024-05-29","cited_by_count":85,"area":null},{"id":"2508.10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","created":"2025-08-14","cited_by_count":82,"area":null},{"id":"2412.03079","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","created":"2024-12-04","cited_by_count":79,"area":null},{"id":"2504.14899","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation","created":"2025-04-21","cited_by_count":77,"area":null},{"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":"2403.14548","title":"DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video","created":"2024-03-21","cited_by_count":64,"area":null},{"id":"2406.15339","title":"Image Conductor: Precision Control for Interactive Video Synthesis","created":"2024-06-21","cited_by_count":63,"area":null},{"id":"2404.15259","title":"FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent","created":"2024-04-23","cited_by_count":61,"area":null},{"id":"2401.01887","title":"LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry","created":"2024-01-03","cited_by_count":56,"area":null},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50,"area":null},{"id":"2506.03140","title":"CamCloneMaster: Enabling Reference-based Camera Control for Video Generation","created":"2025-06-03","cited_by_count":46,"area":null},{"id":"2507.18255","title":"LONG3R: Long Sequence Streaming 3D Reconstruction","created":"2025-07-24","cited_by_count":45,"area":null},{"id":"2411.08380","title":"EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation","created":"2024-11-13","cited_by_count":41,"area":null},{"id":"2506.05558","title":"On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images","created":"2025-06-05","cited_by_count":36,"area":null},{"id":"2411.10836","title":"AnimateAnything: Consistent and Controllable Animation for Video Generation","created":"2024-11-16","cited_by_count":35,"area":null},{"id":"2503.22268","title":"Segment Any Motion in Videos","created":"2025-03-28","cited_by_count":35,"area":null},{"id":"2503.21761","title":"Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video","created":"2025-03-27","cited_by_count":29,"area":null},{"id":"2504.17788","title":"Dynamic Camera Poses and Where to Find Them","created":"2025-04-24","cited_by_count":27,"area":null},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","cited_by_count":25,"area":null},{"id":"2312.09523","title":"DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos","created":"2023-12-15","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":"2411.18650","title":"RoMo: Robust Motion Segmentation Improves Structure from Motion","created":"2024-11-27","cited_by_count":20,"area":null},{"id":"2503.23282","title":"AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos","created":"2025-03-30","cited_by_count":18,"area":null},{"id":"2501.01425","title":"Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation","created":"2025-01-02","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":"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":"2503.15855","title":"VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling","created":"2025-03-20","cited_by_count":14,"area":null},{"id":"2509.26639","title":"Benchmarking Egocentric Visual-Inertial SLAM at City Scale","created":"2025-09-30","cited_by_count":14,"area":null},{"id":"2503.20776","title":"Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields","created":"2025-03-26","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":"2408.10739","title":"TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks","created":"2024-08-20","cited_by_count":12,"area":null},{"id":"2508.11379","title":"G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration","created":"2025-08-15","cited_by_count":12,"area":null},{"id":"2404.09991","title":"EgoPet: Egomotion and Interaction Data from an Animal's Perspective","created":"2024-04-15","cited_by_count":11,"area":null},{"id":"2504.06264","title":"D$^2$USt3R: Enhancing 3D Reconstruction for Dynamic Scenes","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2306.02000","title":"Context-PIPs: Persistent Independent Particles Demands Spatial Context Features","created":"2023-06-03","cited_by_count":9,"area":null},{"id":"2504.12356","title":"Regist3R: Incremental Registration with Stereo Foundation Model","created":"2025-04-16","cited_by_count":9,"area":null},{"id":"2510.14960","title":"C4D: 4D Made from 3D through Dual Correspondences","created":"2025-10-16","cited_by_count":8,"area":null},{"id":"2410.08530","title":"Ego3DT: Tracking Every 3D Object in Ego-centric Videos","created":"2024-10-11","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":"2604.22482","title":"Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond","created":"2026-04-24","cited_by_count":7,"area":null},{"id":"2411.19141","title":"On Moving Object Segmentation from Monocular Video with Transformers","created":"2024-11-28","cited_by_count":6,"area":null},{"id":"2411.13291","title":"DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild","created":"2024-11-20","cited_by_count":4,"area":null},{"id":"2412.01300","title":"MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking","created":"2024-12-02","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":"2503.10464","title":"Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2512.00771","title":"EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes","created":"2025-11-30","cited_by_count":3,"area":null},{"id":"2603.02134","title":"OnlineX: Unified Online 3D Reconstruction and Understanding with Active-to-Stable State Evolution","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.05330","title":"Dark3R: Learning Structure from Motion in the Dark","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2607.27194","title":"VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2401.08937","title":"ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2407.06531","title":"Decomposition Betters Tracking Everything Everywhere","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2509.21119","title":"MotionFlow:Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2511.05229","title":"4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos","created":"2025-11-07","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":"2503.07739","title":"SIRE: SE(3) Intrinsic Rigidity Embeddings","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2509.15123","title":"RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes","created":"2025-09-18","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":"2602.05572","title":"ShapeGaussian: High-Fidelity 4D Human Reconstruction in Monocular Videos via Vision Priors","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2605.19797","title":"Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.18153","title":"Robust Multimodal Dynamic Object Segmentation","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.22039","title":"ORBIT++: Benchmarking SfM in the Wild with 360{\\deg} Video","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2610.14698","title":"PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.19729","title":"A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}