{"total":129,"rows":[{"id":"2601.02281","title":"InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams","created":"2026-01-05","cited_by_count":56,"area":null},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39,"area":null},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","cited_by_count":37,"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":"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":"2603.04385","title":"ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training","created":"2026-03-04","cited_by_count":26,"area":null},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"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":"2512.23437","title":"RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction","created":"2025-12-29","cited_by_count":19,"area":null},{"id":"2607.15275","title":"RoboTTT: Context Scaling for Robot Policies","created":"2026-07-16","cited_by_count":19,"area":null},{"id":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"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":"2512.01540","title":"FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention","created":"2025-12-01","cited_by_count":17,"area":null},{"id":"2601.00051","title":"TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Model","created":"2025-12-31","cited_by_count":16,"area":"wm"},{"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":"2602.14941","title":"AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories","created":"2026-02-16","cited_by_count":15,"area":null},{"id":"2604.15239","title":"TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens","created":"2026-04-16","cited_by_count":15,"area":null},{"id":"2602.21204","title":"Test-Time Training with KV Binding Is Secretly Linear Attention","created":"2026-02-24","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":"2602.20160","title":"tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction","created":"2026-02-23","cited_by_count":12,"area":null},{"id":"2604.15284","title":"GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens","created":"2026-04-16","cited_by_count":12,"area":null},{"id":"2601.22615","title":"TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2603.19076","title":"DROID-SLAM in the Wild","created":"2026-03-19","cited_by_count":10,"area":null},{"id":"2511.21317","title":"HTTM: Head-wise Temporal Token Merging for Faster VGGT","created":"2025-11-26","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":"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":"2603.15330","title":"MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2607.05247","title":"Vision Pretraining for Dense Spatial Perception","created":"2026-07-06","cited_by_count":8,"area":null},{"id":"2512.03939","title":"MUT3R: Motion-aware Updating Transformer for Dynamic 3D Reconstruction","created":"2025-12-03","cited_by_count":7,"area":null},{"id":"2512.05354","title":"SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training","created":"2025-12-05","cited_by_count":7,"area":null},{"id":"2601.01204","title":"XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression","created":"2026-01-03","cited_by_count":7,"area":"inference"},{"id":"2605.21472","title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2512.02293","title":"VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM","created":"2025-12-02","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":"2512.19678","title":"WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion","created":"2025-12-22","cited_by_count":6,"area":"diffusion"},{"id":"2604.07279","title":"Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training","created":"2026-04-08","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":"2512.22581","title":"KV-Tracker: Real-Time Pose Tracking with Transformers","created":"2025-12-27","cited_by_count":5,"area":null},{"id":"2602.23814","title":"Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation","created":"2026-02-27","cited_by_count":5,"area":null},{"id":"2604.15237","title":"StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2510.15072","title":"SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2511.22264","title":"DriveVGGT: Calibration-Constrained Visual Geometry Transformers for Multi-Camera Autonomous Driving","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2512.15577","title":"MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priors","created":"2025-12-17","cited_by_count":4,"area":null},{"id":"2605.03359","title":"Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2603.02351","title":"MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2603.03739","title":"PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation","created":"2026-03-04","cited_by_count":3,"area":"mllm"},{"id":"2603.07690","title":"FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry","created":"2026-03-08","cited_by_count":3,"area":"inference"},{"id":"2603.18493","title":"FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2603.20588","title":"RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction","created":"2026-03-21","cited_by_count":3,"area":null},{"id":"2603.23023","title":"Cog3DMap: Multi-View Vision-Language Reasoning with 3D Cognitive Maps","created":"2026-03-24","cited_by_count":3,"area":"lr"},{"id":"2603.25819","title":"Geo$^\\textbf{2}$: Geometry-Guided Cross-view Geo-Localization and Image Synthesis","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2604.07350","title":"Fast Spatial Memory with Elastic Test-Time Training","created":"2026-04-08","cited_by_count":3,"area":null},{"id":"2605.02772","title":"Linearizing Vision Transformer with Test-Time Training","created":"2026-05-04","cited_by_count":3,"area":null},{"id":"2605.09644","title":"Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval","created":"2026-05-10","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":"2605.25308","title":"Stabilizing Streaming Video Geometry via Dynamic Feature Normalization","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2609.08848","title":"FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2603.15433","title":"Real-Time Human Frontal View Synthesis from a Single Image","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2603.21436","title":"PAS3R: Pose-Adaptive Streaming 3D Reconstruction for Long Video Sequences","created":"2026-03-22","cited_by_count":2,"area":null},{"id":"2603.23413","title":"I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generation","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2604.05351","title":"AnyImageNav: Any-View Geometry for Precise Last-Meter Image-Goal Navigation","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2605.15852","title":"GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction","created":"2026-05-15","cited_by_count":2,"area":"inference"},{"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":"2607.00375","title":"LIST3R: Long-sequence Instance-aware 3D Reconstruction","created":"2026-07-01","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":"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":"2603.05959","title":"OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer","created":"2026-03-06","cited_by_count":1,"area":"inference"},{"id":"2603.09819","title":"ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation","created":"2026-03-10","cited_by_count":1,"area":"diffusion"},{"id":"2604.03878","title":"Learning 3D Reconstruction with Priors in Test Time","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2604.22686","title":"SS3D: End2End Self-Supervised 3D from Web Videos","created":"2026-04-24","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":"2605.06270","title":"Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction","created":"2026-05-07","cited_by_count":1,"area":"inference"},{"id":"2605.14315","title":"TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.16258","title":"IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.16981","title":"Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction","created":"2026-05-16","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":"2606.16960","title":"SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Driving","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2606.21562","title":"Compressing History into Memory: Distilling Transformers into Recurrent Transformers","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2606.30047","title":"Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.02711","title":"RayTun3R: Online Camera Adaptation in 3D Foundation Models","created":"2026-07-02","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":"2608.08132","title":"ASV3D: Adapting Diffusion-Based Single-View 3D Reconstruction with Extra Imagery","created":"2026-08-08","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":"2609.09145","title":"Point4D: Long-range 4D Motion Reconstruction","created":"2026-09-08","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":"2512.05398","title":"The Dynamic Prior: Understanding 3D Structures for Casual Dynamic Videos","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2602.21780","title":"XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression","created":"2026-02-25","cited_by_count":0,"area":"inference"},{"id":"2603.09968","title":"ReCoSplat: Online Feed-Forward Gaussian Splatting via Render-and-Compare","created":"2026-03-10","cited_by_count":0,"area":"inference"},{"id":"2603.14765","title":"SSR: A Training-Free Approach for Streaming 3D Reconstruction","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.27084","title":"SceneExpander: Text-Guided 3D Scene Expansion via Free-Form View Insertion","created":"2026-03-28","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":"2605.17303","title":"LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.21131","title":"UniT: Unified Geometry Learning with Group Autoregressive Transformer","created":"2026-05-20","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}],"next_cursor":"100"}