{"total":136,"rows":[{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692,"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":"2507.16443","title":"VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences","created":"2025-07-22","cited_by_count":115,"area":null},{"id":"2507.07982","title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","created":"2025-07-10","cited_by_count":96,"area":"wm"},{"id":"2507.00416","title":"Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding","created":"2025-07-01","cited_by_count":58,"area":"vla"},{"id":"2510.03198","title":"Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft","created":"2025-10-03","cited_by_count":52,"area":"wm"},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39,"area":null},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2604.08542","title":"Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction","created":"2026-04-09","cited_by_count":31,"area":null},{"id":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29,"area":null},{"id":"2601.19887","title":"VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction","created":"2026-01-27","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":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2507.22885","title":"Viser: Imperative, Web-based 3D Visualization in Python","created":"2025-07-30","cited_by_count":23,"area":null},{"id":"2602.13172","title":"LongStream: Long-Sequence Streaming Autoregressive Visual Geometry","created":"2026-02-13","cited_by_count":23,"area":null},{"id":"2511.10560","title":"OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer","created":"2025-11-13","cited_by_count":22,"area":null},{"id":"2508.17972","title":"SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization","created":"2025-08-25","cited_by_count":20,"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":"2510.13800","title":"Reasoning in Space via Grounding in the World","created":"2025-10-15","cited_by_count":19,"area":"lr"},{"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":"2507.17596","title":"PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving","created":"2025-07-23","cited_by_count":16,"area":"driving"},{"id":"2509.01584","title":"ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association","created":"2025-09-01","cited_by_count":16,"area":null},{"id":"2603.00905","title":"pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning","created":"2026-03-01","cited_by_count":14,"area":"lr"},{"id":"2509.16909","title":"SLAM-Former: Putting SLAM into One Transformer","created":"2025-09-21","cited_by_count":9,"area":null},{"id":"2512.01850","title":"Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching","created":"2025-12-01","cited_by_count":9,"area":"diffusion"},{"id":"2601.06806","title":"SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation","created":"2026-01-11","cited_by_count":9,"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":"2512.21078","title":"UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer","created":"2025-12-24","cited_by_count":8,"area":null},{"id":"2602.05508","title":"VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency","created":"2026-02-05","cited_by_count":8,"area":null},{"id":"2603.16736","title":"World Reconstruction From Inconsistent Views","created":"2026-03-17","cited_by_count":8,"area":"diffusion"},{"id":"2605.26103","title":"Global Structure-from-Motion Meets Feedforward Reconstruction","created":"2026-05-25","cited_by_count":8,"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":"2512.11508","title":"On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models","created":"2025-12-12","cited_by_count":7,"area":null},{"id":"2605.21472","title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2507.19474","title":"DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representations","created":"2025-07-25","cited_by_count":6,"area":null},{"id":"2509.20757","title":"MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2512.13680","title":"LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction","created":"2025-12-15","cited_by_count":6,"area":null},{"id":"2604.14025","title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2511.01186","title":"LiDAR-VGGT: Cross-Modal Coarse-to-Fine Fusion for Globally Consistent and Metric-Scale Dense Mapping","created":"2025-11-03","cited_by_count":5,"area":null},{"id":"2512.02341","title":"TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction","created":"2025-12-02","cited_by_count":5,"area":null},{"id":"2512.22581","title":"KV-Tracker: Real-Time Pose Tracking with Transformers","created":"2025-12-27","cited_by_count":5,"area":null},{"id":"2607.09225","title":"Glob3R: Global Structure-from-Motion with 3D Foundation Models","created":"2026-07-10","cited_by_count":4,"area":"wm"},{"id":"2512.06368","title":"HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos","created":"2025-12-06","cited_by_count":3,"area":null},{"id":"2601.16020","title":"Keyframe-Based Feed-Forward Visual Odometry","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2602.04517","title":"S-MUSt3R: Sliding Multi-view 3D Reconstruction","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2602.18906","title":"Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimates","created":"2026-02-21","cited_by_count":3,"area":null},{"id":"2603.07690","title":"FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry","created":"2026-03-08","cited_by_count":3,"area":"inference"},{"id":"2603.20588","title":"RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction","created":"2026-03-21","cited_by_count":3,"area":null},{"id":"2603.22893","title":"SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2604.26567","title":"AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2605.17478","title":"Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory","created":"2026-05-17","cited_by_count":3,"area":"ssm"},{"id":"2508.13488","title":"ROVER: Robust Loop Closure Verification with Trajectory Prior in Repetitive Environments","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2511.17207","title":"SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2602.04251","title":"Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directions","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2603.16844","title":"M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2604.28115","title":"FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2605.19539","title":"Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2605.26519","title":"$R^3$: 3D Reconstruction via Relative Regression","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2605.27372","title":"G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2606.05035","title":"Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2606.06627","title":"What Matters When Cotraining Robot Manipulation Policies on Everyday Human Videos?","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2607.14481","title":"Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency","created":"2026-07-16","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":"2608.25956","title":"4DGS-WAM: Bridging Past and Future with an Object-Centric World Action Model based on 4D Gaussian Splatting","created":"2026-08-26","cited_by_count":2,"area":"wm"},{"id":"2506.23207","title":"TVG-SLAM: Robust Gaussian Splatting SLAM with Tri-view Geometric Constraints","created":"2025-06-29","cited_by_count":1,"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":"2511.16282","title":"Building temporally coherent 3D maps with VGGT for memory-efficient Semantic SLAM","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2512.01889","title":"KM-ViPE: Online Tightly Coupled Vision-Language-Geometry Fusion for Open-Vocabulary Semantic SLAM","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2512.06868","title":"Dynamic Visual SLAM using a General 3D Prior","created":"2025-12-07","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":"2602.18709","title":"IRIS-SLAM: Unified Geo-Instance Representations for Robust Semantic Localization and Mapping","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2603.17165","title":"SLAM Adversarial Lab: An Extensible Framework for Visual SLAM Robustness Evaluation under Adverse Conditions","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2603.21055","title":"SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2603.26810","title":"Unblur-SLAM: Dense Neural SLAM for Blurry Inputs","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.09480","title":"Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.26067","title":"RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.05749","title":"Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction","created":"2026-05-07","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":"2605.13741","title":"LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.17327","title":"Efficient Feature-Free Initialization for Monocular Visual-Inertial Systems Using a Feed-Forward 3D Model","created":"2026-05-17","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":"2607.06023","title":"Why does Deep Learning Improve Visual SLAM?","created":"2026-07-07","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":"2607.22147","title":"Visual Relocalization from Sparse Views in Aliased and Low-Texture Environments via Novel View Synthesis","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2608.00925","title":"Look Up and Look Back: Hidden Attention and Latent Orientation in a Frozen Foundation Model for Panoramic SLAM","created":"2026-08-02","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":"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":"2608.15260","title":"VGGT-Align: Bridging Local Reconstruction and Global Consistency for Long-Sequence 3D Reconstruction","created":"2026-08-15","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":"2609.11129","title":"ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2609.21437","title":"Think Locally, Refine Globally for Memory-Efficient 3D Reconstruction","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2510.03348","title":"Monocular Visual Odometry without Calibration or Test-time Optimization","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2511.22860","title":"MARVO: Marine-Adaptive Radiance-aware Visual Odometry","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.24212","title":"RANGER: A Monocular Zero-Shot Semantic Navigation Framework through Visual Contextual Adaptation","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2512.25008","title":"FoundationSLAM: Unleashing the Power of Depth Foundation Models for End-to-End Dense Visual SLAM","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2603.12657","title":"VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.16016","title":"FlatLands: Generative Floormap Completion From a Single Egocentric View","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.21785","title":"Online Adaptation of Visual Odometry Frontends with Image-Conditioned Reinforcement Learning","created":"2026-03-23","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}