{"total":30,"rows":[{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2605.23889","title":"HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction","created":"2026-05-22","cited_by_count":9,"area":null},{"id":"2608.01186","title":"QuerySplat: Decoupling Geometry and Appearance Representations in 3DGS Prediction","created":"2026-08-02","cited_by_count":3,"area":null},{"id":"2605.26519","title":"$R^3$: 3D Reconstruction via Relative Regression","created":"2026-05-26","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":"2607.27194","title":"VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2609.04958","title":"MINT: A Unified Model for World-Space Camera and Hand Motion Estimation from Scalable Egocentric Pipeline Supervision","created":"2026-09-04","cited_by_count":2,"area":null},{"id":"2606.08284","title":"G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2607.03612","title":"SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2608.03429","title":"SLAMFormer-$\\infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.27529","title":"Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2608.28288","title":"GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2605.06317","title":"NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.17303","title":"LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.23892","title":"Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.27367","title":"SpatialBench: Is Your Spatial Foundation Model an All-Round Player?","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.05801","title":"TRIG: Trajectory-Rig Decoupled Metric Geometry Learning","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.10441","title":"Context by Distinct Information: An Auditable Dirichlet-Process Working Memory for Long, Redundant Context Streams","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.17389","title":"GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assembly","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.00923","title":"On-the-Fly3R: Towards Robust Online 3D Reconstruction with Feed-Forward 3R Models for Large-Scale UAV Scenarios","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.13733","title":"FFVO: A Feedforward Pose Decoder for Long-Horizon Visual Odometry","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.15795","title":"SURE-Map: Self-Correcting Streaming Geometric Foundation Models","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.35743","title":"InfiniHand: Streaming World-Space Hand Motion Estimation from Egocentric Video","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.40244","title":"StreamRig: Exploiting Intra-Rig Geometry for Streaming Multi-Camera Odometry","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01210","title":"EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01927","title":"CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05207","title":"F$^2$ SLAM: Turning Feed-Forward Geometry into Persistent Factors for SLAM","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.12282","title":"Slot3R: Set-Associative Spatial Memory for Streaming 3D Reconstruction","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12568","title":"MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.16945","title":"UniMetric: Universal Metric Scale Recovery for Visual Geometry Foundation Models","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}