{"total":73,"rows":[{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319,"area":null},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314,"area":null},{"id":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161,"area":null},{"id":"2505.12549","title":"VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold","created":"2025-05-18","cited_by_count":136,"area":null},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"area":null},{"id":"2511.15706","title":"RoMa v2: Harder Better Faster Denser Feature Matching","created":"2025-11-19","cited_by_count":51,"area":null},{"id":"2507.18255","title":"LONG3R: Long Sequence Streaming 3D Reconstruction","created":"2025-07-24","cited_by_count":45,"area":null},{"id":"2511.07321","title":"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting","created":"2025-11-10","cited_by_count":37,"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":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2511.20343","title":"AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend","created":"2025-11-25","cited_by_count":20,"area":null},{"id":"2602.23361","title":"VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale","created":"2026-02-26","cited_by_count":18,"area":null},{"id":"2509.01584","title":"ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association","created":"2025-09-01","cited_by_count":16,"area":null},{"id":"2506.02265","title":"Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction","created":"2025-06-02","cited_by_count":11,"area":null},{"id":"2503.07561","title":"Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression","created":"2025-03-10","cited_by_count":10,"area":null},{"id":"2507.08448","title":"Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT","created":"2025-07-11","cited_by_count":10,"area":null},{"id":"2504.17636","title":"A Guide to Structureless Visual Localization","created":"2025-04-24","cited_by_count":9,"area":null},{"id":"2510.11605","title":"ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2506.04619","title":"Deep Learning Reforms Image Matching: A Survey and Outlook","created":"2025-06-05","cited_by_count":7,"area":null},{"id":"2503.07204","title":"Endo-FASt3r: Endoscopic Foundation model Adaptation for Structure from motion","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2506.23863","title":"Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction","created":"2025-06-30","cited_by_count":5,"area":null},{"id":"2510.00978","title":"A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2510.18714","title":"PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2511.17309","title":"MuM: Multi-View Masked Image Modeling for 3D Vision","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2512.21883","title":"Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer","created":"2025-12-26","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":"2512.06147","title":"GuideNav: User-Informed Development of a Vision-Only Robotic Navigation Assistant For Blind Travelers","created":"2025-12-05","cited_by_count":4,"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":"2509.23038","title":"GeLoc3r: Enhancing Relative Camera Pose Regression with Geometric Consistency Regularization","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2511.05404","title":"Multi-modal Loop Closure Detection with Foundation Models in Severely Unstructured Environments","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2604.22390","title":"Region Matters: Efficient and Reliable Region-Aware Visual Place Recognition","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2509.23555","title":"From Fields to Splats: A Cross-Domain Survey of Real-Time Neural Scene Representations","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2511.13864","title":"GRLoc: Geometric Representation Regression for Visual Localization","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2512.09065","title":"ShelfAware: Real-Time Semantic Localization in Quasi-Static Environments with Low-Cost Sensors","created":"2025-12-09","cited_by_count":1,"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":"2606.31086","title":"CasaMaestro: Multi-View Panoramas for House-Scale 3D Reconstruction","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.04722","title":"Reference-Induced Consensus for Selective Posed-Reference Visual Localization","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.01706","title":"UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2609.01530","title":"Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2509.24236","title":"PROFusion: Robust and Accurate Dense Reconstruction via Camera Pose Regression and Optimization","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2512.12165","title":"Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2512.17226","title":"Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2601.02730","title":"HOLO: Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on SD Maps","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.12291","title":"OpenNavMap: Multi-Session Appearance-Based Topometric Mapping for Scalable Visual Navigation","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2602.03198","title":"From Single Scan to Sequential Consistency: A New Paradigm for LIDAR Relocalization","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.06968","title":"Learning to Anchor Visual Odometry: KAN-Based Pose Regression for Planetary Landing","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2603.10893","title":"S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.19625","title":"IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.20818","title":"PlanaReLoc: Camera Relocalization in 3D Planar Primitives via Region-Based Structure Matching","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2603.27170","title":"MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localization","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.03814","title":"InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.05402","title":"LSGS-Loc: Towards Robust 3DGS-Based Visual Localization for Large-Scale UAV Scenarios","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.12068","title":"Privacy-Preserving Structureless Visual Localization via Image Obfuscation","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.13476","title":"RobotPan: A 360$^\\circ$ Surround-View Robotic Vision System for Embodied Perception","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.15495","title":"GIST: Multimodal Knowledge Extraction and Spatial Grounding via Intelligent Semantic Topology","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.15814","title":"Continual Hand-Eye Calibration for Open-world Robotic Manipulation","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.07351","title":"Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.10204","title":"3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects","created":"2026-05-11","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":"2606.03287","title":"BA-T: An Iterative Transformer for Two-View Bundle Adjustment","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.02486","title":"GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.09815","title":"RASR: Range-Aware Scale Recovery for Metric UAV Navigation","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.17268","title":"PACE: Polar Axis-Conditioned Estimation for PairUAV Relative Localization","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.07116","title":"Geometry-Aware Camera Localization for Bronchoscopy","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.12442","title":"MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.02798","title":"AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.04201","title":"Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction","created":"2026-09-03","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":"2609.18465","title":"GeoCond: A Conditioning-Aware Reliability Adapter for Feed-Forward 3D Reconstruction","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.25907","title":"NaCR: Visual Localization via NeRF-aided Camera Ray Regression","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.36432","title":"Temporal-Aware Fusion for Robust Outdoor LiDAR Localization","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38755","title":"Agentic Relative Camera Pose Estimation via Learned Ranking and Verification","created":"2026-09-30","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}],"next_cursor":null}