{"total":141,"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":"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":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40,"area":null},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","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":"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":"2509.14117","title":"GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model","created":"2025-09-17","cited_by_count":26,"area":"vla"},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2509.07120","title":"Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers","created":"2025-09-08","cited_by_count":23,"area":null},{"id":"2510.27234","title":"MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts","created":"2025-10-31","cited_by_count":21,"area":"moe"},{"id":"2506.21348","title":"PanSt3R: Multi-view Consistent Panoptic Segmentation","created":"2025-06-26","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":"2508.16433","title":"HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction","created":"2025-08-22","cited_by_count":15,"area":null},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2512.04686","title":"Towards Cross-View Point Correspondence in Vision-Language Models","created":"2025-12-04","cited_by_count":14,"area":"mllm"},{"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":"2509.18778","title":"VGGT-DP: Generalizable Robot Control via Vision Foundation Models","created":"2025-09-23","cited_by_count":11,"area":"offlinerl"},{"id":"2602.21552","title":"Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction","created":"2026-02-25","cited_by_count":11,"area":null},{"id":"2603.22883","title":"Group Editing: Edit Multiple Images in One Go","created":"2026-03-24","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":"2511.14751","title":"Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers","created":"2025-11-18","cited_by_count":10,"area":"inference"},{"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":"2504.12356","title":"Regist3R: Incremental Registration with Stereo Foundation Model","created":"2025-04-16","cited_by_count":9,"area":null},{"id":"2601.01222","title":"UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass","created":"2026-01-03","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":"2510.20776","title":"CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling","created":"2025-10-23","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":"2602.14021","title":"Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow","created":"2026-02-15","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":"2511.21945","title":"GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence","created":"2025-11-26","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":"2603.23502","title":"OccAny: Generalized Unconstrained Urban 3D Occupancy","created":"2026-03-24","cited_by_count":6,"area":null},{"id":"2603.28896","title":"Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses","created":"2026-03-30","cited_by_count":6,"area":null},{"id":"2509.23258","title":"OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting","created":"2025-09-27","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":"2512.02341","title":"TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction","created":"2025-12-02","cited_by_count":5,"area":null},{"id":"2512.21883","title":"Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer","created":"2025-12-26","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":"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":"2601.08831","title":"3AM: 3egment Anything with Geometric Consistency in Videos","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2602.05321","title":"Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning","created":"2026-02-05","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":"2604.18260","title":"Geometry-Guided 3D Visual Token Pruning for Video-Language Models","created":"2026-04-20","cited_by_count":4,"area":"mllm"},{"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":"2509.26455","title":"Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2511.03099","title":"DentalSplat: Dental Occlusion Novel View Synthesis from Sparse Intra-Oral Photographs","created":"2025-11-05","cited_by_count":3,"area":null},{"id":"2511.20620","title":"Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI","created":"2025-11-25","cited_by_count":3,"area":null},{"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":"2602.00865","title":"Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware","created":"2026-01-31","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":"2603.19926","title":"SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2603.22851","title":"UniQueR: Unified Query-based Feedforward 3D Reconstruction","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":"2605.25308","title":"Stabilizing Streaming Video Geometry via Dynamic Feature Normalization","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2605.26115","title":"TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2511.00998","title":"GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies","created":"2025-11-02","cited_by_count":2,"area":"diffusion"},{"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":"2511.17364","title":"SVRecon: Sparse Voxel Rasterization for Surface Reconstruction","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2602.23224","title":"UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.01194","title":"RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations","created":"2026-03-01","cited_by_count":2,"area":null},{"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":"2603.14498","title":"R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2603.16099","title":"OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2603.17625","title":"S-VGGT: Structure-Aware Subscene Decomposition for Scalable 3D Foundation Models","created":"2026-03-18","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":"2605.04435","title":"Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes","created":"2026-05-06","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":"2607.19228","title":"IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2608.13147","title":"Geometry-Grounded Unified 3D Perception for Autonomous Driving","created":"2026-08-13","cited_by_count":2,"area":null},{"id":"2511.09818","title":"Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2512.23667","title":"MVID: Feed-Forward Multi-View Intrinsic Image Decomposition","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2601.06035","title":"Investigating Anthropometric Fidelity in SAM 3D Body","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2601.11729","title":"SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models","created":"2026-01-16","cited_by_count":1,"area":"lr"},{"id":"2603.05959","title":"OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer","created":"2026-03-06","cited_by_count":1,"area":"inference"},{"id":"2604.03878","title":"Learning 3D Reconstruction with Priors in Test Time","created":"2026-04-04","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":"2606.14307","title":"Pano3D: Unified 3D Reconstruction and Panoptic Segmentation","created":"2026-06-12","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":"2606.25245","title":"OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.01885","title":"Diversity-aware View Partitioning for Scalable VGGT","created":"2026-07-02","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":"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":"2609.03931","title":"Sparse auto-regressive modeling for scene generation from multi-view images","created":"2026-09-03","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":"2609.15018","title":"G-ray: Ray-Level Relative Geometric Position Encoding in Multi-View Vision Transformers under Camera Heterogeneity","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2609.22687","title":"PanoSeg3R: Feed-Forward 3D Semantic Segmentation for Panoramic Images with an Automatic Data Curation Pipeline","created":"2026-09-19","cited_by_count":1,"area":null},{"id":"2609.25490","title":"SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2508.16026","title":"NeuralMeshing: Complete Object Mesh Extraction from Casual Captures","created":"2025-08-22","cited_by_count":0,"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":"2511.14315","title":"Dental3R: Geometry-Aware Pairing for Intraoral 3D Reconstruction from Sparse-View Photographs","created":"2025-11-18","cited_by_count":0,"area":null}],"next_cursor":"100"}