{"total":314,"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":"2510.10726","title":"WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting","created":"2025-10-12","cited_by_count":67,"area":null},{"id":"2512.08924","title":"Efficiently Reconstructing Dynamic Scenes One D4RT at a Time","created":"2025-12-09","cited_by_count":54,"area":null},{"id":"2511.15706","title":"RoMa v2: Harder Better Faster Denser Feature Matching","created":"2025-11-19","cited_by_count":51,"area":null},{"id":"2601.00393","title":"NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos","created":"2026-01-01","cited_by_count":46,"area":"wm"},{"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":"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":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40,"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":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","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":"2510.13802","title":"Trace Anything: Representing Any Video in 4D via Trajectory Fields","created":"2025-10-15","cited_by_count":33,"area":null},{"id":"2601.04090","title":"Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction","created":"2026-01-07","cited_by_count":31,"area":"diffusion"},{"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":"2603.07145","title":"LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models","created":"2026-03-07","cited_by_count":28,"area":"wm"},{"id":"2510.21615","title":"Epipolar Geometry Improves Video Generation Models","created":"2025-10-24","cited_by_count":26,"area":"diffusion"},{"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":"2601.13029","title":"Think3D: Thinking with Space for Spatial Reasoning","created":"2026-01-19","cited_by_count":24,"area":"lr"},{"id":"2603.26599","title":"VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward","created":"2026-03-27","cited_by_count":24,"area":"diffusion"},{"id":"2601.11514","title":"ShapeR: Robust Conditional 3D Shape Generation from Casual Captures","created":"2026-01-16","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":"2511.20343","title":"AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend","created":"2025-11-25","cited_by_count":20,"area":null},{"id":"2512.23437","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":"2602.23361","title":"VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale","created":"2026-02-26","cited_by_count":18,"area":null},{"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":"2512.01540","title":"FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention","created":"2025-12-01","cited_by_count":17,"area":null},{"id":"2606.09828","title":"Latent Spatial Memory for Video World Models","created":"2026-06-08","cited_by_count":17,"area":"wm"},{"id":"2512.02541","title":"AVGGT: Rethinking Global Attention for Accelerating VGGT","created":"2025-12-02","cited_by_count":16,"area":null},{"id":"2603.22275","title":"Repurposing Geometric Foundation Models for Multi-view Diffusion","created":"2026-03-23","cited_by_count":15,"area":"diffusion"},{"id":"2603.00697","title":"TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction","created":"2026-02-28","cited_by_count":14,"area":null},{"id":"2607.09024","title":"Video Generation Models are General-Purpose Vision Learners","created":"2026-07-10","cited_by_count":14,"area":null},{"id":"2512.15715","title":"In Pursuit of Pixel Supervision for Visual Pre-training","created":"2025-12-17","cited_by_count":13,"area":null},{"id":"2602.00807","title":"Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds","created":"2026-01-31","cited_by_count":13,"area":"vla"},{"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":"2512.13660","title":"Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2601.16982","title":"AnyView: Synthesizing Any Novel View in Dynamic Scenes","created":"2026-01-23","cited_by_count":12,"area":null},{"id":"2603.13615","title":"Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis","created":"2026-03-13","cited_by_count":12,"area":"wm"},{"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":"2606.27537","title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","created":"2026-06-25","cited_by_count":12,"area":"wm"},{"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":"2606.17046","title":"Geometric Action Model for Robot Policy Learning","created":"2026-06-15","cited_by_count":11,"area":"wm"},{"id":"2512.02870","title":"Taming Camera-Controlled Video Generation with Verifiable Geometry Reward","created":"2025-12-02","cited_by_count":10,"area":"diffusion"},{"id":"2603.05078","title":"MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer","created":"2026-03-05","cited_by_count":9,"area":null},{"id":"2512.14364","title":"Unified Semantic Transformer for 3D Scene Understanding","created":"2025-12-16","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":"2601.09452","title":"MAD: Motion Appearance Decoupling for efficient Driving World Models","created":"2026-01-14","cited_by_count":8,"area":"wm"},{"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":"2602.14021","title":"Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow","created":"2026-02-15","cited_by_count":8,"area":null},{"id":"2603.12193","title":"SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics","created":"2026-03-12","cited_by_count":8,"area":"vla"},{"id":"2603.16736","title":"World Reconstruction From Inconsistent Views","created":"2026-03-17","cited_by_count":8,"area":"diffusion"},{"id":"2604.07053","title":"AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors","created":"2026-04-08","cited_by_count":8,"area":null},{"id":"2605.26103","title":"Global Structure-from-Motion Meets Feedforward Reconstruction","created":"2026-05-25","cited_by_count":8,"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":"2603.25053","title":"GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generator","created":"2026-03-26","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2511.15396","title":"ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation","created":"2025-11-19","cited_by_count":6,"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":"2512.21003","title":"MVInverse: Feed-forward Multi-view Inverse Rendering in Seconds","created":"2025-12-24","cited_by_count":6,"area":null},{"id":"2603.07660","title":"Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence","created":"2026-03-08","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":"2606.13432","title":"OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data","created":"2026-06-11","cited_by_count":6,"area":null},{"id":"2509.24421","title":"Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting","created":"2025-09-29","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":"2512.19020","title":"CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2512.20770","title":"OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspective","created":"2025-12-23","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":"2601.05116","title":"From Rays to Projections: Better Inputs for Feed-Forward View Synthesis","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2603.02413","title":"TruckDrive: Long-Range Autonomous Highway Driving Dataset","created":"2026-03-02","cited_by_count":5,"area":"driving"},{"id":"2603.25739","title":"MegaFlow: Zero-Shot Large Displacement Optical Flow","created":"2026-03-26","cited_by_count":5,"area":null},{"id":"2604.01479","title":"RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space","created":"2026-04-01","cited_by_count":5,"area":null},{"id":"2604.09429","title":"Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories","created":"2026-04-10","cited_by_count":5,"area":null},{"id":"2605.12587","title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","created":"2026-05-12","cited_by_count":5,"area":"diffusion"},{"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":"2607.22534","title":"SM4RT: Learning Structured Motion Geometry for 4D Reconstruction","created":"2026-07-24","cited_by_count":5,"area":null},{"id":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2512.02006","title":"MV-TAP: Tracking Any Point in Multi-View Videos","created":"2025-12-01","cited_by_count":4,"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":"2512.16908","title":"SceneDiff: A Benchmark and Method for Multiview Object Change Detection","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2512.19402","title":"Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface","created":"2025-12-22","cited_by_count":4,"area":null},{"id":"2512.24385","title":"Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems","created":"2025-12-30","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":"2602.05321","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":"2604.00548","title":"Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2604.06830","title":"VGGT-SLAM++","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2605.03359","title":"Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2605.05207","title":"Syn4D: A Multiview Synthetic 4D Dataset","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2605.24642","title":"Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models","created":"2026-05-23","cited_by_count":4,"area":"vla"},{"id":"2605.30115","title":"Large Depth Completion Model from Sparse Observations","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2607.09225","title":"Glob3R: Global Structure-from-Motion with 3D Foundation Models","created":"2026-07-10","cited_by_count":4,"area":"wm"},{"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":"2511.18115","title":"Muskie: Multi-view Masked Image Modeling for 3D Vision Pre-training","created":"2025-11-22","cited_by_count":3,"area":null}],"next_cursor":"100"}