{"total":327,"rows":[{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044,"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":"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":"2501.09898","title":"FoundationStereo: Zero-Shot Stereo Matching","created":"2025-01-17","cited_by_count":173,"area":null},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173,"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":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110,"area":null},{"id":"2503.22236","title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","created":"2025-03-28","cited_by_count":99,"area":null},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","cited_by_count":89,"area":null},{"id":"2412.03079","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","created":"2024-12-04","cited_by_count":79,"area":null},{"id":"2504.14899","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation","created":"2025-04-21","cited_by_count":77,"area":null},{"id":"2412.14015","title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation","created":"2024-12-18","cited_by_count":74,"area":null},{"id":"2410.22128","title":"PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting","created":"2024-10-29","cited_by_count":62,"area":null},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62,"area":null},{"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":"2604.20329","title":"Image Generators are Generalist Vision Learners","created":"2026-04-22","cited_by_count":43,"area":null},{"id":"2503.13265","title":"FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis","created":"2025-03-17","cited_by_count":37,"area":null},{"id":"2503.07535","title":"LBM: Latent Bridge Matching for Fast Image-to-Image Translation","created":"2025-03-10","cited_by_count":36,"area":null},{"id":"2505.10565","title":"Depth Anything with Any Prior","created":"2025-05-15","cited_by_count":36,"area":null},{"id":"2505.10696","title":"TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation","created":"2025-05-15","cited_by_count":36,"area":null},{"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":"2504.07958","title":"Detect Anything 3D in the Wild","created":"2025-04-10","cited_by_count":33,"area":null},{"id":"2505.20290","title":"EgoZero: Robot Learning from Smart Glasses","created":"2025-05-26","cited_by_count":33,"area":null},{"id":"2411.19278","title":"OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration","created":"2024-11-28","cited_by_count":30,"area":null},{"id":"2411.19189","title":"Video Depth without Video Models","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2503.21761","title":"Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video","created":"2025-03-27","cited_by_count":29,"area":null},{"id":"2412.18153","title":"DepthLab: From Partial to Complete","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2504.17788","title":"Dynamic Camera Poses and Where to Find Them","created":"2025-04-24","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":"2504.20040","title":"MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion","created":"2025-04-28","cited_by_count":26,"area":null},{"id":"2504.05692","title":"POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction","created":"2025-04-08","cited_by_count":25,"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":"2411.16833","title":"Open Vocabulary Monocular 3D Object Detection","created":"2024-11-25","cited_by_count":23,"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":"2410.22332","title":"Local Policies Enable Zero-shot Long-horizon Manipulation","created":"2024-10-29","cited_by_count":22,"area":null},{"id":"2501.12981","title":"UniUIR: Considering Underwater Image Restoration as An All-in-One Learner","created":"2025-01-22","cited_by_count":22,"area":null},{"id":"2412.14166","title":"MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data","created":"2024-12-18","cited_by_count":21,"area":null},{"id":"2504.05303","title":"InteractVLM: 3D Interaction Reasoning from 2D Foundational Models","created":"2025-04-07","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":"2501.05446","title":"Relative Pose Estimation through Affine Corrections of Monocular Depth Priors","created":"2025-01-09","cited_by_count":18,"area":null},{"id":"2503.23282","title":"AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos","created":"2025-03-30","cited_by_count":18,"area":null},{"id":"2502.08769","title":"Cluster and Predict Latent Patches for Improved Masked Image Modeling","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2509.18090","title":"GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction","created":"2025-09-22","cited_by_count":17,"area":null},{"id":"2501.12218","title":"Exploring Temporally-Aware Features for Point Tracking","created":"2025-01-21","cited_by_count":15,"area":null},{"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":"2508.04611","title":"BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment","created":"2025-08-06","cited_by_count":15,"area":null},{"id":"2504.07093","title":"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution","created":"2025-04-09","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":"2504.14687","title":"Seurat: From Moving Points to Depth","created":"2025-04-20","cited_by_count":13,"area":null},{"id":"2602.14662","title":"Advances in Global Solvers for 3D Vision","created":"2026-02-16","cited_by_count":13,"area":null},{"id":"2502.13078","title":"L4P: Towards Unified Low-Level 4D Vision Perception","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2507.01634","title":"Depth Anything at Any Condition","created":"2025-07-02","cited_by_count":12,"area":null},{"id":"2508.08588","title":"RealisMotion: Decomposed Human Motion Control and Video Generation in the World Space","created":"2025-08-12","cited_by_count":12,"area":null},{"id":"2503.12745","title":"ProtoDepth: Unsupervised Continual Depth Completion with Prototypes","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2504.11092","title":"Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting","created":"2025-04-15","cited_by_count":11,"area":null},{"id":"2506.13110","title":"GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction","created":"2025-06-16","cited_by_count":11,"area":null},{"id":"2507.15365","title":"DAViD: Data-efficient and Accurate Vision Models from Synthetic Data","created":"2025-07-21","cited_by_count":11,"area":null},{"id":"2507.23567","title":"3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection","created":"2025-07-31","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":"2501.07742","title":"RePoseD: Efficient Relative Pose Estimation With Known Depth Information","created":"2025-01-13","cited_by_count":10,"area":null},{"id":"2509.05297","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2601.22054","title":"MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2604.02329","title":"Generative World Renderer","created":"2026-04-02","cited_by_count":10,"area":null},{"id":"2604.03723","title":"SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation","created":"2026-04-04","cited_by_count":10,"area":null},{"id":"2412.03428","title":"2DGS-Room: Seed-Guided 2D Gaussian Splatting with Geometric Constrains for High-Fidelity Indoor Scene Reconstruction","created":"2024-12-04","cited_by_count":9,"area":null},{"id":"2508.04928","title":"Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens","created":"2025-08-06","cited_by_count":9,"area":null},{"id":"2508.14466","title":"LookOut: Real-World Humanoid Egocentric Navigation","created":"2025-08-20","cited_by_count":9,"area":null},{"id":"2509.01469","title":"Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars","created":"2025-09-01","cited_by_count":9,"area":null},{"id":"2601.00796","title":"AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstruction","created":"2026-01-02","cited_by_count":9,"area":null},{"id":"2502.04640","title":"Building Rome with Convex Optimization","created":"2025-02-07","cited_by_count":8,"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":"2507.04451","title":"CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step","created":"2025-07-06","cited_by_count":8,"area":null},{"id":"2508.13995","title":"Self-Supervised Sparse Sensor Fusion for Long Range Perception","created":"2025-08-19","cited_by_count":8,"area":null},{"id":"2509.11301","title":"UnLoc: Leveraging Depth Uncertainties for Floorplan Localization","created":"2025-09-14","cited_by_count":8,"area":null},{"id":"2510.17568","title":"PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception","created":"2025-10-20","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":"2503.22462","title":"SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations","created":"2025-03-28","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":"2506.17450","title":"BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing","created":"2025-06-20","cited_by_count":7,"area":null},{"id":"2506.17960","title":"GeNIE: A Generalizable Navigation System for In-the-Wild Environments","created":"2025-06-22","cited_by_count":7,"area":null},{"id":"2512.08358","title":"TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels","created":"2025-12-09","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":"2411.16319","title":"CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation","created":"2024-11-25","cited_by_count":6,"area":null},{"id":"2503.00746","title":"DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting","created":"2025-03-02","cited_by_count":6,"area":null},{"id":"2503.14786","title":"SketchSplat: 3D Edge Reconstruction via Differentiable Multi-view Sketch Splatting","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2506.02493","title":"Towards In-the-wild 3D Plane Reconstruction from a Single Image","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2510.09320","title":"Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2601.01676","title":"LabelAny3D: Label Any Object 3D in the Wild","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2603.01650","title":"PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts","created":"2026-03-02","cited_by_count":6,"area":null},{"id":"2412.02336","title":"Amodal Depth Anything: Amodal Depth Estimation in the Wild","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2503.15470","title":"EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2503.17182","title":"Radar-Guided Polynomial Fitting for Metric Depth Estimation","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2507.14505","title":"DCHM: Depth-Consistent Human Modeling for Multiview Detection","created":"2025-07-19","cited_by_count":5,"area":null}],"next_cursor":"100"}