{"total":319,"rows":[{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2509.02560","title":"FastVGGT: Training-Free Acceleration of Visual Geometry Transformer","created":"2025-09-02","cited_by_count":98,"area":"inference"},{"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":"2512.08924","title":"Efficiently Reconstructing Dynamic Scenes One D4RT at a Time","created":"2025-12-09","cited_by_count":54,"area":null},{"id":"2511.21688","title":"G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning","created":"2025-11-26","cited_by_count":44,"area":"lr"},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39,"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":"2509.05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","created":"2025-09-05","cited_by_count":35,"area":null},{"id":"2601.09499","title":"V-DPM: 4D Video Reconstruction with Dynamic Point Maps","created":"2026-01-14","cited_by_count":34,"area":null},{"id":"2511.23075","title":"SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models","created":"2025-11-28","cited_by_count":26,"area":"lr"},{"id":"2604.21686","title":"WorldMark: A Unified Benchmark Suite for Interactive Video World Models","created":"2026-04-23","cited_by_count":26,"area":"wm"},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2512.02015","title":"Generative Video Motion Editing with 3D Point Tracks","created":"2025-12-01","cited_by_count":23,"area":null},{"id":"2601.23286","title":"VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation","created":"2026-01-30","cited_by_count":23,"area":"diffusion"},{"id":"2602.13172","title":"LongStream: Long-Sequence Streaming Autoregressive Visual Geometry","created":"2026-02-13","cited_by_count":23,"area":null},{"id":"2512.04012","title":"Emergent Outlier View Rejection in Visual Geometry Grounded Transformers","created":"2025-12-03","cited_by_count":22,"area":null},{"id":"2602.10094","title":"4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere","created":"2026-02-10","cited_by_count":22,"area":null},{"id":"2512.16919","title":"DVGT: Driving Visual Geometry Transformer","created":"2025-12-18","cited_by_count":21,"area":null},{"id":"2604.07209","title":"INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling","created":"2026-04-08","cited_by_count":21,"area":"wm"},{"id":"2512.23437","title":"RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction","created":"2025-12-29","cited_by_count":19,"area":null},{"id":"2602.04476","title":"Vision-aligned Latent Reasoning for Multi-modal Large Language Model","created":"2026-02-04","cited_by_count":18,"area":"lr"},{"id":"2602.06037","title":"Thinking with Geometry: Active Geometry Integration for Spatial Reasoning","created":"2026-02-05","cited_by_count":18,"area":"lr"},{"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":"2606.13673","title":"SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning","created":"2026-06-11","cited_by_count":17,"area":"lr"},{"id":"2603.22275","title":"Repurposing Geometric Foundation Models for Multi-view Diffusion","created":"2026-03-23","cited_by_count":15,"area":"diffusion"},{"id":"2606.14048","title":"WAM4D: Fast 4D World Action Model via Spatial Register Tokens","created":"2026-06-12","cited_by_count":15,"area":"wm"},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2602.04877","title":"CoWTracker: Tracking by Warping instead of Correlation","created":"2026-02-04","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":"2603.12655","title":"VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model","created":"2026-03-13","cited_by_count":13,"area":"wm"},{"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":"2512.20557","title":"Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models","created":"2025-12-23","cited_by_count":12,"area":"lr"},{"id":"2510.13454","title":"Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator","created":"2025-10-15","cited_by_count":11,"area":null},{"id":"2512.09619","title":"GLaD: Geometric Latent Distillation for Vision-Language-Action Models","created":"2025-12-10","cited_by_count":11,"area":"lr"},{"id":"2512.15508","title":"Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting","created":"2025-12-17","cited_by_count":11,"area":null},{"id":"2602.17951","title":"ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models","created":"2026-02-20","cited_by_count":11,"area":"vla"},{"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":"2512.02870","title":"Taming Camera-Controlled Video Generation with Verifiable Geometry Reward","created":"2025-12-02","cited_by_count":10,"area":"diffusion"},{"id":"2603.02697","title":"ShareVerse: Multi-Agent Consistent Video Generation for Shared World Modeling","created":"2026-03-03","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":"2602.09765","title":"NavDreamer: Video Models as Zero-Shot 3D Navigators","created":"2026-02-10","cited_by_count":9,"area":"vla"},{"id":"2602.20157","title":"Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning","created":"2026-02-23","cited_by_count":9,"area":null},{"id":"2603.05078","title":"MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer","created":"2026-03-05","cited_by_count":9,"area":null},{"id":"2603.20176","title":"LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis","created":"2026-03-20","cited_by_count":9,"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":"2603.26639","title":"Make Geometry Matter for Spatial Reasoning","created":"2026-03-27","cited_by_count":8,"area":"lr"},{"id":"2601.01050","title":"EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos","created":"2026-01-03","cited_by_count":7,"area":"diffusion"},{"id":"2603.11421","title":"ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation","created":"2026-03-12","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":"2602.15733","title":"MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction","created":"2026-02-17","cited_by_count":6,"area":"deeprl"},{"id":"2602.21186","title":"Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning","created":"2026-02-24","cited_by_count":6,"area":"lr"},{"id":"2603.25336","title":"HeSS: Head Sensitivity Score for Sparsity Redistribution in VGGT","created":"2026-03-26","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":"2604.14025","title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2605.30215","title":"D\\'ej\\`a View: Looping Transformers for Multi-View 3D Reconstruction","created":"2026-05-28","cited_by_count":6,"area":null},{"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":"2511.17309","title":"MuM: Multi-View Masked Image Modeling for 3D Vision","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2602.05789","title":"Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiation","created":"2026-02-05","cited_by_count":5,"area":"lr"},{"id":"2602.06159","title":"Driving with DINO: Vision Foundation Features as a Unified Bridge for Sim-to-Real Generation in Autonomous Driving","created":"2026-02-05","cited_by_count":5,"area":"diffusion"},{"id":"2602.23814","title":"Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation","created":"2026-02-27","cited_by_count":5,"area":null},{"id":"2603.08592","title":"Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations","created":"2026-03-09","cited_by_count":5,"area":"lr"},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","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":"2606.05102","title":"ZipSplat: Fewer Gaussians, Better Splats","created":"2026-06-03","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":"2608.13391","title":"Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation","created":"2026-08-13","cited_by_count":5,"area":"distill"},{"id":"2511.22264","title":"DriveVGGT: Calibration-Constrained Visual Geometry Transformers for Multi-Camera Autonomous Driving","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2602.02331","title":"TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2602.02402","title":"SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation","created":"2026-02-02","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":"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":"2603.12265","title":"OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams","created":"2026-03-12","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":"2604.00548","title":"Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations","created":"2026-04-01","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":"2604.19747","title":"AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model","created":"2026-04-21","cited_by_count":4,"area":"diffusion"},{"id":"2605.05207","title":"Syn4D: A Multiview Synthetic 4D Dataset","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2605.15182","title":"Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.15876","title":"Unlocking Dense Metric Depth Estimation in VLMs","created":"2026-05-15","cited_by_count":4,"area":"mllm"},{"id":"2606.15162","title":"GeoStream: Toward Precise Camera Controlled Streaming Video Generation","created":"2026-06-13","cited_by_count":4,"area":"wm"},{"id":"2607.05373","title":"PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space","created":"2026-07-06","cited_by_count":4,"area":"diffusion"},{"id":"2607.10840","title":"OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields","created":"2026-07-12","cited_by_count":4,"area":"wm"},{"id":"2511.23191","title":"GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2512.08498","title":"On-the-fly Large-scale 3D Reconstruction from Multi-Camera Rigs","created":"2025-12-09","cited_by_count":3,"area":null},{"id":"2512.09373","title":"FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)$^N$ Diffusion Refinement","created":"2025-12-10","cited_by_count":3,"area":null},{"id":"2601.16020","title":"Keyframe-Based Feed-Forward Visual Odometry","created":"2026-01-22","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":"2602.00865","title":"Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2602.14751","title":"Depth Completion as Parameter-Efficient Test-Time Adaptation","created":"2026-02-16","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":"2603.01765","title":"StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion","created":"2026-03-02","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":"2603.16461","title":"GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models","created":"2026-03-17","cited_by_count":3,"area":"lr"},{"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":"2603.19926","title":"SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2603.22893","title":"SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2603.24836","title":"WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2604.04707","title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","created":"2026-04-06","cited_by_count":3,"area":"wm"},{"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"}],"next_cursor":"100"}