{"total":205,"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":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314,"area":null},{"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":"2505.20279","title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","created":"2025-05-26","cited_by_count":166,"area":"mllm"},{"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":"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":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91,"area":null},{"id":"2507.02863","title":"Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory","created":"2025-07-03","cited_by_count":87,"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":"2506.08015","title":"4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos","created":"2025-06-09","cited_by_count":49,"area":null},{"id":"2510.13375","title":"DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning","created":"2025-10-15","cited_by_count":46,"area":"lr"},{"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":"2506.09278","title":"UFM: A Simple Path towards Unified Dense Correspondence with Flow","created":"2025-06-10","cited_by_count":36,"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":"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":"2503.22430","title":"MVSAnywhere: Zero-Shot Multi-View Stereo","created":"2025-03-28","cited_by_count":26,"area":null},{"id":"2602.13172","title":"LongStream: Long-Sequence Streaming Autoregressive Visual Geometry","created":"2026-02-13","cited_by_count":23,"area":null},{"id":"2507.03737","title":"Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps","created":"2025-07-04","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":"2509.01708","title":"Articulated Object Estimation in the Wild","created":"2025-09-01","cited_by_count":19,"area":null},{"id":"2503.12701","title":"AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration","created":"2025-03-16","cited_by_count":18,"area":null},{"id":"2512.04939","title":"LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging","created":"2025-12-04","cited_by_count":17,"area":"inference"},{"id":"2509.01584","title":"ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association","created":"2025-09-01","cited_by_count":16,"area":null},{"id":"2504.07093","title":"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution","created":"2025-04-09","cited_by_count":14,"area":null},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2509.26639","title":"Benchmarking Egocentric Visual-Inertial SLAM at City Scale","created":"2025-09-30","cited_by_count":14,"area":null},{"id":"2505.05592","title":"Learning to Drive Anywhere with Model-Based Reannotation","created":"2025-05-08","cited_by_count":13,"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":"2508.14160","title":"RynnEC: Bringing MLLMs into Embodied World","created":"2025-08-19","cited_by_count":11,"area":"mllm"},{"id":"2503.21082","title":"Can Video Diffusion Model Reconstruct 4D Geometry?","created":"2025-03-27","cited_by_count":10,"area":"diffusion"},{"id":"2511.04595","title":"UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction","created":"2025-11-06","cited_by_count":10,"area":null},{"id":"2503.20000","title":"The Coralscapes Dataset: Semantic Scene Understanding in Coral Reefs","created":"2025-03-25","cited_by_count":9,"area":null},{"id":"2509.16909","title":"SLAM-Former: Putting SLAM into One Transformer","created":"2025-09-21","cited_by_count":9,"area":null},{"id":"2510.08551","title":"ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation","created":"2025-10-09","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":"2605.23889","title":"HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction","created":"2026-05-22","cited_by_count":9,"area":null},{"id":"2503.24009","title":"Learning 3D-Gaussian Simulators from RGB Videos","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2601.06874","title":"MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation","created":"2026-01-11","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":"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":"2510.20818","title":"VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation","created":"2025-10-23","cited_by_count":7,"area":"vla"},{"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":"2512.13680","title":"LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction","created":"2025-12-15","cited_by_count":6,"area":null},{"id":"2503.17358","title":"Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2504.04457","title":"VSLAM-LAB: A Comprehensive Framework for Visual SLAM Methods and Datasets","created":"2025-04-06","cited_by_count":5,"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":"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":"2605.22819","title":"Cambrian-P: Pose-Grounded Video Understanding","created":"2026-05-21","cited_by_count":5,"area":null},{"id":"2509.23541","title":"OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction","created":"2025-09-28","cited_by_count":4,"area":null},{"id":"2511.18290","title":"SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes","created":"2025-11-23","cited_by_count":4,"area":null},{"id":"2512.08625","title":"OpenMonoGS-SLAM: Monocular Gaussian Splatting SLAM with Open-set Semantics","created":"2025-12-09","cited_by_count":4,"area":null},{"id":"2512.08930","title":"Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment","created":"2025-12-09","cited_by_count":4,"area":null},{"id":"2601.08831","title":"3AM: 3egment Anything with Geometric Consistency in Videos","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2602.04439","title":"TrajVG: 3D Trajectory-Coupled Visual Geometry Learning","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2603.17355","title":"OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2604.06830","title":"VGGT-SLAM++","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2604.08532","title":"Self-Improving 4D Perception via Self-Distillation","created":"2026-04-09","cited_by_count":4,"area":"distill"},{"id":"2607.09225","title":"Glob3R: Global Structure-from-Motion with 3D Foundation Models","created":"2026-07-10","cited_by_count":4,"area":"wm"},{"id":"2506.06909","title":"Gaussian Mapping for Evolving Scenes","created":"2025-06-07","cited_by_count":3,"area":null},{"id":"2510.07119","title":"MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency","created":"2025-10-08","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":"2601.22046","title":"PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction","created":"2026-01-29","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":"2602.21967","title":"Dream-SLAM: Dreaming the Unseen for Active SLAM in Dynamic Environments","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2602.22091","title":"Learning to Drive is a Free Gift: Large-Scale Label-Free Autonomy Pretraining from Unposed In-The-Wild Videos","created":"2026-02-25","cited_by_count":3,"area":null},{"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":"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":"2605.25308","title":"Stabilizing Streaming Video Geometry via Dynamic Feature Normalization","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2504.14135","title":"Unreal Robotics Lab: A High-Fidelity Robotics Simulator with Advanced Physics and Rendering","created":"2025-04-19","cited_by_count":2,"area":null},{"id":"2505.23756","title":"Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.06517","title":"GS4: Generalizable Sparse Splatting Semantic SLAM","created":"2025-06-06","cited_by_count":2,"area":null},{"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":"2508.15972","title":"UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation","created":"2025-08-21","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":"2602.22716","title":"SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs","created":"2026-02-26","cited_by_count":2,"area":"mllm"},{"id":"2603.03765","title":"LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving","created":"2026-03-04","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":"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":"2609.05416","title":"WorldSculpt: Generating Compositional Worlds from Grounded Videos","created":"2026-09-04","cited_by_count":2,"area":null},{"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":"2508.07885","title":"Autonomous Navigation of Cloud-Controlled Quadcopters in Confined Spaces Using Multi-Modal Perception and LLM-Driven High Semantic Reasoning","created":"2025-08-11","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}],"next_cursor":"100"}