{"total":102,"rows":[{"id":"2505.23716","title":"AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views","created":"2025-05-29","cited_by_count":243,"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":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109,"area":"mllm"},{"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":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91,"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":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"area":null},{"id":"2507.18255","title":"LONG3R: Long Sequence Streaming 3D Reconstruction","created":"2025-07-24","cited_by_count":45,"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":"2507.10065","title":"MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second","created":"2025-07-14","cited_by_count":35,"area":null},{"id":"2509.05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","created":"2025-09-05","cited_by_count":35,"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":"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":"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":"2602.13172","title":"LongStream: Long-Sequence Streaming Autoregressive Visual Geometry","created":"2026-02-13","cited_by_count":23,"area":null},{"id":"2506.13750","title":"Test3R: Learning to Reconstruct 3D at Test Time","created":"2025-06-16","cited_by_count":20,"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":"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":"2503.21082","title":"Can Video Diffusion Model Reconstruct 4D Geometry?","created":"2025-03-27","cited_by_count":10,"area":"diffusion"},{"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":"2507.22052","title":"Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos","created":"2025-07-29","cited_by_count":10,"area":null},{"id":"2511.18416","title":"4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2509.16909","title":"SLAM-Former: Putting SLAM into One Transformer","created":"2025-09-21","cited_by_count":9,"area":null},{"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":"2507.18541","title":"Unposed 3DGS Reconstruction with Probabilistic Procrustes Mapping","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2507.21960","title":"PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction","created":"2025-07-29","cited_by_count":8,"area":null},{"id":"2510.20776","title":"CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling","created":"2025-10-23","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":"2508.17811","title":"MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting","created":"2025-08-25","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":"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":"2509.23737","title":"GRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent State","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2512.21691","title":"Analyzing the Mechanism of Attention Collapse in VGGT from a Dynamics Perspective","created":"2025-12-25","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":"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":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"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":"2603.25993","title":"FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentation","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2508.07908","title":"Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction","created":"2025-08-11","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":"2512.01296","title":"EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly","created":"2025-12-01","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":"2603.18493","title":"FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction","created":"2026-03-19","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":"2605.23903","title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2510.20605","title":"OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2511.13121","title":"CloseUpShot: Close-up Novel View Synthesis from Sparse-views via Point-conditioned Diffusion Model","created":"2025-11-17","cited_by_count":2,"area":"diffusion"},{"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":"2603.18510","title":"OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2603.26837","title":"SpatialAnt: Autonomous Zero-Shot Robot Navigation via Active Scene Reconstruction and Visual Anticipation","created":"2026-03-27","cited_by_count":2,"area":"mllm"},{"id":"2605.22423","title":"Moment-Reenacting: Inverse Motion Degradation with Cross-shutter Guidance","created":"2026-05-21","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":"2512.06868","title":"Dynamic Visual SLAM using a General 3D Prior","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2601.14895","title":"SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA","created":"2026-01-21","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":"2604.28193","title":"Generalizable Sparse-View 3D Reconstruction from Unconstrained Images","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.10275","title":"PolarVSR: A Unified Framework and Benchmark for Continuous Space-Time Polarization Video Reconstruction","created":"2026-05-11","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":"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":"2608.27529","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":"2609.13504","title":"RIGOR: Rig-Informed Geometry for Omnidirectional Reconstruction","created":"2026-09-11","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":"2512.14032","title":"ACE-SLAM: Scene Coordinate Regression for Neural Implicit Real-Time SLAM","created":"2025-12-16","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":"2601.05584","title":"GS-DMSR: Dynamic Sensitive Multi-scale Manifold Enhancement for Accelerated High-Quality 3D Gaussian Splatting","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2603.06971","title":"SurgCUT3R: Surgical Scene-Aware Continuous Understanding of Temporal 3D Representation","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2603.11298","title":"InstantHDR: Single-forward Gaussian Splatting Initialization for HDR 3D Reconstruction","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.12551","title":"Cross-Attentive Multiview Fusion of Vision-Language Embeddings","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"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":"2605.07978","title":"Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images","created":"2026-05-08","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":"2605.19656","title":"Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.15211","title":"MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos","created":"2026-07-16","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":"2608.29705","title":"A Calibration Audit of Confidence in Feed-Forward 3D Reconstruction Models","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2608.30690","title":"Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.03824","title":"VI3: Grounding Pretrained 3D Foundation Models with Inertial Cues","created":"2026-09-03","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":"2609.05210","title":"BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular Priors","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.09418","title":"Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Exploration","created":"2026-09-08","cited_by_count":0,"area":"wm"},{"id":"2609.12747","title":"Assisted Spatial Cognition Through Vision-Language Models","created":"2026-09-11","cited_by_count":0,"area":"mllm"},{"id":"2609.13903","title":"SkyAnchor: Updating Metric-scale Aerial 3D Gaussian Scenes from Unposed Ground-View Sequences","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.19518","title":"AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backend","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.21502","title":"Adaptive World Memory 3D Foundation Model for Scalable 3D Mapping, Localization, and Rendering","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.23049","title":"VDGS: Visibility-Driven Large-Scale 3D Gaussian Splatting for Aerial Scene Reconstruction","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.28064","title":"SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference","created":"2026-09-23","cited_by_count":0,"area":"wm"},{"id":"2609.38054","title":"Pow3R-SLAM: Real-Time RGB-D SLAM with 3D Reconstruction Priors","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":"100"}