{"total":302,"rows":[{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567,"area":null},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983,"area":null},{"id":"2410.24207","title":"No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images","created":"2024-10-31","cited_by_count":248,"area":null},{"id":"2409.19152","title":"MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion","created":"2024-09-27","cited_by_count":162,"area":null},{"id":"2503.18945","title":"Aether: Geometric-Aware Unified World Modeling","created":"2025-03-24","cited_by_count":97,"area":"wm"},{"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":"2412.16334","title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","created":"2024-12-20","cited_by_count":79,"area":null},{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67,"area":"agents"},{"id":"2410.22128","title":"PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting","created":"2024-10-29","cited_by_count":62,"area":null},{"id":"2506.05348","title":"FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction","created":"2025-06-05","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":"2501.14914","title":"Light3R-SfM: Towards Feed-forward Structure-from-Motion","created":"2025-01-24","cited_by_count":47,"area":null},{"id":"2411.17190","title":"SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting","created":"2024-11-26","cited_by_count":42,"area":null},{"id":"2412.09573","title":"FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction","created":"2024-12-12","cited_by_count":41,"area":null},{"id":"2508.01171","title":"No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views","created":"2025-08-02","cited_by_count":40,"area":null},{"id":"2404.08928","title":"DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector","created":"2024-04-13","cited_by_count":39,"area":null},{"id":"2407.01511","title":"CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents","created":"2024-07-01","cited_by_count":39,"area":"mllm"},{"id":"2504.13157","title":"AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis","created":"2025-04-17","cited_by_count":39,"area":null},{"id":"2511.07321","title":"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting","created":"2025-11-10","cited_by_count":37,"area":null},{"id":"2506.09278","title":"UFM: A Simple Path towards Unified Dense Correspondence with Flow","created":"2025-06-10","cited_by_count":36,"area":null},{"id":"2408.08000","title":"MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing","created":"2024-08-15","cited_by_count":30,"area":null},{"id":"2412.09072","title":"Cross-View Completion Models are Zero-shot Correspondence Estimators","created":"2024-12-12","cited_by_count":30,"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":"2512.04012","title":"Emergent Outlier View Rejection in Visual Geometry Grounded Transformers","created":"2025-12-03","cited_by_count":22,"area":null},{"id":"2512.04021","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","created":"2025-12-03","cited_by_count":21,"area":null},{"id":"2507.23277","title":"iLRM: An Iterative Large 3D Reconstruction Model","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2411.02229","title":"FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training","created":"2024-11-04","cited_by_count":18,"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":"2502.08769","title":"Cluster and Predict Latent Patches for Improved Masked Image Modeling","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2406.19568","title":"How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach","created":"2024-06-27","cited_by_count":16,"area":"diffusion"},{"id":"2309.16992","title":"Segment Anything Model is a Good Teacher for Local Feature Learning","created":"2023-09-29","cited_by_count":15,"area":null},{"id":"2501.14277","title":"Dense-SfM: Structure from Motion with Dense Consistent Matching","created":"2025-01-24","cited_by_count":15,"area":null},{"id":"2508.16433","title":"HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction","created":"2025-08-22","cited_by_count":15,"area":null},{"id":"2503.03437","title":"JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba","created":"2025-03-05","cited_by_count":14,"area":"ssm"},{"id":"2503.17731","title":"Co-op: Correspondence-based Novel Object Pose Estimation","created":"2025-03-22","cited_by_count":14,"area":null},{"id":"2503.19358","title":"From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting","created":"2025-03-25","cited_by_count":14,"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":"2509.24878","title":"ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation","created":"2025-09-29","cited_by_count":14,"area":null},{"id":"2410.12269","title":"LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment","created":"2024-10-16","cited_by_count":13,"area":null},{"id":"2503.07347","title":"DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection","created":"2025-03-10","cited_by_count":13,"area":"deeprl"},{"id":"2504.08291","title":"DreamFuse: Adaptive Image Fusion with Diffusion Transformer","created":"2025-04-11","cited_by_count":13,"area":"diffusion"},{"id":"2505.08013","title":"RDD: Robust Feature Detector and Descriptor using Deformable Transformer","created":"2025-05-12","cited_by_count":13,"area":null},{"id":"2501.14945","title":"MATCHA:Towards Matching Anything","created":"2025-01-24","cited_by_count":12,"area":null},{"id":"2503.23925","title":"CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matching","created":"2025-03-31","cited_by_count":12,"area":null},{"id":"2509.18350","title":"OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata","created":"2025-09-22","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":"2604.04931","title":"LoMa: Local Feature Matching Revisited","created":"2026-04-06","cited_by_count":11,"area":null},{"id":"2307.00485","title":"TopicFM+: Boosting Accuracy and Efficiency of Topic-Assisted Feature Matching","created":"2023-07-02","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":"2503.07561","title":"Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression","created":"2025-03-10","cited_by_count":10,"area":null},{"id":"2501.16679","title":"Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion","created":"2025-01-28","cited_by_count":9,"area":null},{"id":"2502.01002","title":"Multi-Resolution SAR and Optical Remote Sensing Image Registration Methods: A Review, Datasets, and Future Perspectives","created":"2025-02-03","cited_by_count":9,"area":null},{"id":"2504.17636","title":"A Guide to Structureless Visual Localization","created":"2025-04-24","cited_by_count":9,"area":null},{"id":"2507.04839","title":"RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction","created":"2025-07-07","cited_by_count":9,"area":"deeprl"},{"id":"2601.05239","title":"Plenoptic Video Generation","created":"2026-01-08","cited_by_count":9,"area":null},{"id":"2602.20157","title":"Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning","created":"2026-02-23","cited_by_count":9,"area":null},{"id":"2404.00838","title":"3MOS: Multi-sources, Multi-resolutions, and Multi-scenes dataset for Optical-SAR image matching","created":"2024-04-01","cited_by_count":8,"area":null},{"id":"2501.01949","title":"VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment","created":"2025-01-03","cited_by_count":8,"area":null},{"id":"2502.19955","title":"RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2503.06831","title":"One-Shot Dual-Arm Imitation Learning","created":"2025-03-10","cited_by_count":8,"area":"offlinerl"},{"id":"2503.08664","title":"MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention","created":"2025-03-11","cited_by_count":8,"area":"diffusion"},{"id":"2506.04224","title":"Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset","created":"2025-06-04","cited_by_count":8,"area":null},{"id":"2510.14874","title":"TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions","created":"2025-10-16","cited_by_count":8,"area":null},{"id":"2603.16736","title":"World Reconstruction From Inconsistent Views","created":"2026-03-17","cited_by_count":8,"area":"diffusion"},{"id":"2407.07789","title":"Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2503.05122","title":"EDM: Efficient Deep Feature Matching","created":"2025-03-07","cited_by_count":7,"area":null},{"id":"2503.24306","title":"Point Tracking in Surgery--The 2024 Surgical Tattoos in Infrared (STIR) Challenge","created":"2025-03-31","cited_by_count":7,"area":null},{"id":"2504.01872","title":"CoMatcher: Multi-View Collaborative Feature Matching","created":"2025-04-02","cited_by_count":7,"area":null},{"id":"2506.04619","title":"Deep Learning Reforms Image Matching: A Survey and Outlook","created":"2025-06-05","cited_by_count":7,"area":null},{"id":"2506.04803","title":"SupeRANSAC: One RANSAC to Rule Them All","created":"2025-06-05","cited_by_count":7,"area":null},{"id":"2506.06026","title":"O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2506.13697","title":"Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry","created":"2025-06-16","cited_by_count":7,"area":null},{"id":"2509.17246","title":"SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views","created":"2025-09-21","cited_by_count":7,"area":null},{"id":"2405.15660","title":"Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition","created":"2024-05-24","cited_by_count":6,"area":null},{"id":"2408.14186","title":"Affine steerers for structured keypoint description","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2410.11394","title":"MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fields","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2410.22733","title":"ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses","created":"2024-10-30","cited_by_count":6,"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":"2511.22686","title":"Emergent Extreme-View Geometry in 3D Foundation Models","created":"2025-11-27","cited_by_count":6,"area":null},{"id":"2407.08199","title":"SRPose: Two-view Relative Pose Estimation with Sparse Keypoints","created":"2024-07-11","cited_by_count":5,"area":null},{"id":"2411.09484","title":"Image Matching Filtering and Refinement by Planes and Beyond","created":"2024-11-14","cited_by_count":5,"area":null},{"id":"2502.00462","title":"MambaGlue: Fast and Robust Local Feature Matching With Mamba","created":"2025-02-01","cited_by_count":5,"area":"ssm"},{"id":"2503.16185","title":"MapGlue: Multimodal Remote Sensing Image Matching","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2504.04834","title":"Learning Affine Correspondences by Integrating Geometric Constraints","created":"2025-04-07","cited_by_count":5,"area":null},{"id":"2507.00659","title":"LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment","created":"2025-07-01","cited_by_count":5,"area":null},{"id":"2507.13145","title":"DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2509.09594","title":"ObjectReact: Learning Object-Relative Control for Visual Navigation","created":"2025-09-11","cited_by_count":5,"area":null},{"id":"2509.15548","title":"MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2510.01934","title":"Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2510.05051","title":"SegMASt3R: Geometry Grounded Segment Matching","created":"2025-10-06","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":"2512.21883","title":"Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer","created":"2025-12-26","cited_by_count":5,"area":null},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2408.16445","title":"Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks","created":"2024-08-29","cited_by_count":4,"area":null},{"id":"2410.04419","title":"LiteVLoc: Map-Lite Visual Localization for Image Goal Navigation","created":"2024-10-06","cited_by_count":4,"area":null},{"id":"2412.02245","title":"SparseLGS: Sparse View Language Embedded Gaussian Splatting","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2503.13433","title":"Less Biased Noise Scale Estimation for Threshold-Robust RANSAC","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2506.07670","title":"ProSplat: Improved Feed-Forward 3D Gaussian Splatting for Wide-Baseline Sparse Views","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2507.00392","title":"Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space","created":"2025-07-01","cited_by_count":4,"area":null}],"next_cursor":"100"}