{"total":261,"rows":[{"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":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76,"area":null},{"id":"2510.21571","title":"Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos","created":"2025-10-24","cited_by_count":70,"area":"vla"},{"id":"2602.15989","title":"SAM 3D Body: Robust Full-Body Human Mesh Recovery","created":"2026-02-17","cited_by_count":69,"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":"2605.15178","title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","created":"2026-05-14","cited_by_count":55,"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":"2604.14268","title":"HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds","created":"2026-04-15","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":"2509.25413","title":"DepthLM: Metric Depth From Vision Language Models","created":"2025-09-29","cited_by_count":30,"area":"mllm"},{"id":"2512.16561","title":"N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models","created":"2025-12-18","cited_by_count":29,"area":"lr"},{"id":"2601.05138","title":"VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control","created":"2026-01-08","cited_by_count":28,"area":"wm"},{"id":"2601.17895","title":"Masked Depth Modeling for Spatial Perception","created":"2026-01-25","cited_by_count":28,"area":null},{"id":"2510.07181","title":"TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics","created":"2025-10-08","cited_by_count":27,"area":"lr"},{"id":"2511.22659","title":"Geometrically-Constrained Agent for Spatial Reasoning","created":"2025-11-27","cited_by_count":26,"area":"lr"},{"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":"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":"2603.05449","title":"RealWonder: Real-Time Physical Action-Conditioned Video Generation","created":"2026-03-05","cited_by_count":22,"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":"2510.19400","title":"Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes","created":"2025-10-22","cited_by_count":20,"area":"lr"},{"id":"2507.23277","title":"iLRM: An Iterative Large 3D Reconstruction Model","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2510.13800","title":"Reasoning in Space via Grounding in the World","created":"2025-10-15","cited_by_count":19,"area":"lr"},{"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":"2603.02049","title":"WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories","created":"2026-03-02","cited_by_count":18,"area":"diffusion"},{"id":"2604.21915","title":"Vista4D: Video Reshooting with 4D Point Clouds","created":"2026-04-23","cited_by_count":18,"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":"2604.01001","title":"EgoSim: Egocentric World Simulator for Embodied Interaction Generation","created":"2026-04-01","cited_by_count":14,"area":null},{"id":"2604.08626","title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","created":"2026-04-09","cited_by_count":14,"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":"2604.00813","title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","created":"2026-04-01","cited_by_count":13,"area":"driving"},{"id":"2606.19333","title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","created":"2026-06-17","cited_by_count":13,"area":null},{"id":"2512.13660","title":"Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"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":"2602.09013","title":"Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction","created":"2026-02-09","cited_by_count":11,"area":null},{"id":"2604.04135","title":"NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results","created":"2026-04-05","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":"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":"2603.00515","title":"MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence","created":"2026-02-28","cited_by_count":10,"area":"lr"},{"id":"2606.02753","title":"MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data","created":"2026-06-01","cited_by_count":10,"area":"wm"},{"id":"2606.31672","title":"WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models","created":"2026-06-30","cited_by_count":10,"area":"wm"},{"id":"2510.10287","title":"Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking","created":"2025-10-11","cited_by_count":9,"area":null},{"id":"2602.09765","title":"NavDreamer: Video Models as Zero-Shot 3D Navigators","created":"2026-02-10","cited_by_count":9,"area":"vla"},{"id":"2512.08269","title":"EgoX: Egocentric Video Generation from a Single Exocentric Video","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2602.20119","title":"NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2603.27105","title":"UniDAC: Universal Metric Depth Estimation for Any Camera","created":"2026-03-28","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":"2509.24209","title":"Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2512.22854","title":"ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning","created":"2025-12-28","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"},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2511.22429","title":"Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation","created":"2025-11-27","cited_by_count":6,"area":"distill"},{"id":"2603.00492","title":"ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models","created":"2026-02-28","cited_by_count":6,"area":"diffusion"},{"id":"2606.10135","title":"BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression","created":"2026-06-08","cited_by_count":6,"area":"wm"},{"id":"2606.11324","title":"Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models","created":"2026-06-09","cited_by_count":6,"area":"lr"},{"id":"2510.06469","title":"SIGMA-GEN: Structure and Identity Guided Multi-subject Assembly for Image Generation","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2602.05330","title":"MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2602.23893","title":"AoE: Always-on Egocentric Human Video Collection for Embodied AI","created":"2026-02-27","cited_by_count":5,"area":null},{"id":"2603.05711","title":"Any to Full: Prompting Depth Anything for Depth Completion in One Stage","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2603.29387","title":"Extend3D: Town-Scale 3D Generation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2606.03994","title":"SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2606.13652","title":"World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible","created":"2026-06-11","cited_by_count":5,"area":"diffusion"},{"id":"2510.03896","title":"GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert","created":"2025-10-04","cited_by_count":4,"area":"lr"},{"id":"2510.24464","title":"Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2512.08889","title":"No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers","created":"2025-12-09","cited_by_count":4,"area":"lr"},{"id":"2601.05208","title":"MoE3D: A Mixture-of-Experts Module for 3D Reconstruction","created":"2026-01-08","cited_by_count":4,"area":"moe"},{"id":"2602.04439","title":"TrajVG: 3D Trajectory-Coupled Visual Geometry Learning","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2603.15603","title":"Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery","created":"2026-03-16","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":"2605.30115","title":"Large Depth Completion Model from Sparse Observations","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2606.13676","title":"Modality Forcing for Scalable Spatial Generation","created":"2026-06-11","cited_by_count":4,"area":null},{"id":"2512.11061","title":"VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation","created":"2025-12-11","cited_by_count":3,"area":"wm"},{"id":"2602.14751","title":"Depth Completion as Parameter-Efficient Test-Time Adaptation","created":"2026-02-16","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":"2603.01765","title":"StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2603.03744","title":"DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2603.25411","title":"HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models","created":"2026-03-26","cited_by_count":3,"area":"lr"},{"id":"2604.11331","title":"Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale","created":"2026-04-13","cited_by_count":3,"area":"diffusion"},{"id":"2604.20715","title":"GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers","created":"2026-04-22","cited_by_count":3,"area":"diffusion"},{"id":"2605.17916","title":"PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis","created":"2026-05-18","cited_by_count":3,"area":"wm"},{"id":"2605.20992","title":"Open-CHOIR: Open-World Contact-Aware 4D Hand-Object Interaction Reconstruction","created":"2026-05-20","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":"2605.30060","title":"Towards Consistent Video Geometry Estimation","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.21596","title":"$\\phi$-Scene: Physically Grounded Image-to-3D Scene Reconstruction","created":"2026-06-19","cited_by_count":3,"area":null},{"id":"2606.29716","title":"AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2606.31329","title":"3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance","created":"2026-06-30","cited_by_count":3,"area":"vla"},{"id":"2607.01015","title":"SuperFlex: Deformable Superquadrics for Point Cloud Decomposition","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2607.11588","title":"FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry","created":"2026-07-13","cited_by_count":3,"area":null},{"id":"2607.12993","title":"X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras","created":"2026-07-14","cited_by_count":3,"area":null},{"id":"2608.23486","title":"GeoWAM: Visual Geometry World Action Models for Autonomous Driving","created":"2026-08-24","cited_by_count":3,"area":"wm"},{"id":"2507.11540","title":"Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2510.17157","title":"GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2511.17340","title":"Refracting Reality: Generating Images with Realistic Transparent Objects","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2511.19172","title":"MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2512.10959","title":"StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2512.13597","title":"Lighting in Motion: Spatiotemporal HDR Lighting Estimation","created":"2025-12-15","cited_by_count":2,"area":"diffusion"},{"id":"2512.22819","title":"Depth Anything in $360^\\circ$: Towards Scale Invariance in the Wild","created":"2025-12-28","cited_by_count":2,"area":null},{"id":"2601.03362","title":"Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views","created":"2026-01-06","cited_by_count":2,"area":null}],"next_cursor":"100"}