{"total":299,"rows":[{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"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":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548,"area":null},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319,"area":null},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314,"area":null},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261,"area":null},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207,"area":null},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106,"area":null},{"id":"2412.09401","title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","created":"2024-12-12","cited_by_count":102,"area":null},{"id":"2506.04225","title":"Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation","created":"2025-06-04","cited_by_count":101,"area":"diffusion"},{"id":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94,"area":null},{"id":"2504.13152","title":"St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World","created":"2025-04-17","cited_by_count":89,"area":null},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87,"area":null},{"id":"2412.08376","title":"Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization","created":"2024-12-11","cited_by_count":82,"area":null},{"id":"2504.14717","title":"TAPIP3D: Tracking Any Point in Persistent 3D Geometry","created":"2025-04-20","cited_by_count":69,"area":null},{"id":"2412.06699","title":"You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale","created":"2024-12-09","cited_by_count":65,"area":"diffusion"},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62,"area":null},{"id":"2509.12201","title":"OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling","created":"2025-09-15","cited_by_count":62,"area":"wm"},{"id":"2511.19861","title":"GigaWorld-0: World Models as Data Engine to Empower Embodied AI","created":"2025-11-25","cited_by_count":62,"area":"wm"},{"id":"2510.07316","title":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers","created":"2025-10-08","cited_by_count":51,"area":"diffusion"},{"id":"2502.04299","title":"MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation","created":"2025-02-06","cited_by_count":50,"area":"diffusion"},{"id":"2412.04472","title":"Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail","created":"2024-12-05","cited_by_count":47,"area":null},{"id":"2502.13143","title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","created":"2025-02-18","cited_by_count":46,"area":"lr"},{"id":"2507.16290","title":"Dens3R: A Foundation Model for 3D Geometry Prediction","created":"2025-07-22","cited_by_count":46,"area":null},{"id":"2510.19430","title":"GigaBrain-0: A World Model-Powered Vision-Language-Action Model","created":"2025-10-22","cited_by_count":44,"area":"wm"},{"id":"2604.20329","title":"Image Generators are Generalist Vision Learners","created":"2026-04-22","cited_by_count":43,"area":null},{"id":"2509.19296","title":"Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation","created":"2025-09-23","cited_by_count":41,"area":"diffusion"},{"id":"2510.08568","title":"NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos","created":"2025-10-09","cited_by_count":40,"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":"2504.01016","title":"GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors","created":"2025-04-01","cited_by_count":37,"area":"diffusion"},{"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":"2508.08086","title":"Matrix-3D: Omnidirectional Explorable 3D World Generation","created":"2025-08-11","cited_by_count":35,"area":null},{"id":"2601.17895","title":"Masked Depth Modeling for Spatial Perception","created":"2026-01-25","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":"2503.22430","title":"MVSAnywhere: Zero-Shot Multi-View Stereo","created":"2025-03-28","cited_by_count":26,"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":"2509.26618","title":"DA$^{2}$: Depth Anything in Any Direction","created":"2025-09-30","cited_by_count":25,"area":null},{"id":"2512.16913","title":"Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation","created":"2025-12-18","cited_by_count":25,"area":null},{"id":"2602.11598","title":"ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation","created":"2026-02-12","cited_by_count":25,"area":null},{"id":"2601.03252","title":"InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields","created":"2026-01-06","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":"2512.16919","title":"DVGT: Driving Visual Geometry Transformer","created":"2025-12-18","cited_by_count":21,"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":"2512.10685","title":"Sharp Monocular View Synthesis in Less Than a Second","created":"2025-12-11","cited_by_count":20,"area":null},{"id":"2411.17385","title":"DepthCues: Evaluating Monocular Depth Perception in Large Vision Models","created":"2024-11-26","cited_by_count":19,"area":null},{"id":"2507.23782","title":"MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2501.05446","title":"Relative Pose Estimation through Affine Corrections of Monocular Depth Priors","created":"2025-01-09","cited_by_count":18,"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":"2510.23571","title":"RobotArena $\\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation","created":"2025-10-27","cited_by_count":18,"area":"vla"},{"id":"2512.01030","title":"Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model","created":"2025-11-30","cited_by_count":18,"area":"diffusion"},{"id":"2508.21060","title":"Multi-View 3D Point Tracking","created":"2025-08-28","cited_by_count":17,"area":null},{"id":"2510.15869","title":"Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery","created":"2025-10-17","cited_by_count":17,"area":null},{"id":"2512.10957","title":"SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model","created":"2025-12-11","cited_by_count":17,"area":null},{"id":"2505.11992","title":"SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations","created":"2025-05-17","cited_by_count":16,"area":"diffusion"},{"id":"2502.19204","title":"Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator","created":"2025-02-26","cited_by_count":15,"area":null},{"id":"2503.10745","title":"Unifying 2D and 3D Vision-Language Understanding","created":"2025-03-13","cited_by_count":15,"area":null},{"id":"2508.04611","title":"BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment","created":"2025-08-06","cited_by_count":15,"area":null},{"id":"2505.05473","title":"DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion","created":"2025-05-08","cited_by_count":14,"area":"diffusion"},{"id":"2510.11649","title":"PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image","created":"2025-10-13","cited_by_count":14,"area":null},{"id":"2512.11988","title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","created":"2025-12-12","cited_by_count":14,"area":null},{"id":"2605.10922","title":"Pixal3D: Pixel-Aligned 3D Generation from Images","created":"2026-05-11","cited_by_count":14,"area":null},{"id":"2503.16611","title":"A Recipe for Generating 3D Worlds From a Single Image","created":"2025-03-20","cited_by_count":13,"area":null},{"id":"2505.22859","title":"4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians","created":"2025-05-28","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":"2603.17571","title":"PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery","created":"2026-03-18","cited_by_count":13,"area":null},{"id":"2503.03259","title":"BANet: Bilateral Aggregation Network for Mobile Stereo Matching","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2506.05327","title":"Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting","created":"2025-06-05","cited_by_count":12,"area":null},{"id":"2511.21135","title":"SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation","created":"2025-11-26","cited_by_count":12,"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":"2506.02265","title":"Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction","created":"2025-06-02","cited_by_count":11,"area":null},{"id":"2509.02530","title":"Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots","created":"2025-09-02","cited_by_count":11,"area":null},{"id":"2604.04406","title":"3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image","created":"2026-04-06","cited_by_count":11,"area":null},{"id":"2501.03717","title":"Materialist: Physically Based Editing Using Single-Image Inverse Rendering","created":"2025-01-07","cited_by_count":10,"area":null},{"id":"2501.07742","title":"RePoseD: Efficient Relative Pose Estimation With Known Depth Information","created":"2025-01-13","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":"2511.04595","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":"2512.23705","title":"Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation","created":"2025-12-29","cited_by_count":10,"area":"diffusion"},{"id":"2601.22054","title":"MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2603.08055","title":"Speed3R: Sparse Feed-forward 3D Reconstruction Models","created":"2026-03-09","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":"2505.24521","title":"UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation","created":"2025-05-30","cited_by_count":9,"area":"diffusion"},{"id":"2511.16666","title":"SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation","created":"2025-11-20","cited_by_count":9,"area":null},{"id":"2503.11633","title":"Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation","created":"2025-03-14","cited_by_count":8,"area":null},{"id":"2504.17787","title":"The Fourth Monocular Depth Estimation Challenge","created":"2025-04-24","cited_by_count":8,"area":null},{"id":"2504.18424","title":"LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning","created":"2025-04-25","cited_by_count":8,"area":null},{"id":"2507.18678","title":"Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2508.18213","title":"Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance","created":"2025-08-25","cited_by_count":8,"area":"diffusion"},{"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":"2602.21929","title":"Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context","created":"2026-02-25","cited_by_count":8,"area":null},{"id":"2607.17967","title":"MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement","created":"2026-07-20","cited_by_count":8,"area":null},{"id":"2412.12906","title":"CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image","created":"2024-12-17","cited_by_count":7,"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":"2508.04147","title":"IDCNet: Guided Video Diffusion for Metric-Consistent RGBD Scene Generation with Precise Camera Control","created":"2025-08-06","cited_by_count":7,"area":"diffusion"},{"id":"2601.16192","title":"360Anything: Geometry-Free Lifting of Images and Videos to 360{\\deg}","created":"2026-01-22","cited_by_count":7,"area":null},{"id":"2603.04179","title":"NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction","created":"2026-03-04","cited_by_count":7,"area":null},{"id":"2603.11911","title":"InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model","created":"2026-03-12","cited_by_count":7,"area":"wm"},{"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":"2607.02515","title":"PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation","created":"2026-07-02","cited_by_count":7,"area":"diffusion"}],"next_cursor":"100"}