{"total":87,"rows":[{"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":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367,"area":null},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227,"area":null},{"id":"2502.12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views","created":"2025-02-17","cited_by_count":180,"area":null},{"id":"2311.12024","title":"PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction","created":"2023-11-20","cited_by_count":165,"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":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147,"area":null},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131,"area":null},{"id":"2401.12592","title":"RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos","created":"2024-01-23","cited_by_count":115,"area":null},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87,"area":null},{"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":"2404.14351","title":"Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer","created":"2024-04-22","cited_by_count":73,"area":null},{"id":"2503.17316","title":"Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors","created":"2025-03-21","cited_by_count":72,"area":null},{"id":"2310.01410","title":"LEAP: Liberate Sparse-view 3D Modeling from Camera Poses","created":"2023-10-02","cited_by_count":65,"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":"2502.07685","title":"Matrix3D: Large Photogrammetry Model All-in-One","created":"2025-02-11","cited_by_count":40,"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":"2504.13157","title":"AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis","created":"2025-04-17","cited_by_count":39,"area":null},{"id":"2408.10195","title":"SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views","created":"2024-08-19","cited_by_count":35,"area":"diffusion"},{"id":"2411.16443","title":"SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis","created":"2024-11-25","cited_by_count":34,"area":"diffusion"},{"id":"2412.17806","title":"Reconstructing People, Places, and Cameras","created":"2024-12-23","cited_by_count":31,"area":null},{"id":"2312.00690","title":"Open-vocabulary object 6D pose estimation","created":"2023-12-01","cited_by_count":29,"area":null},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22,"area":null},{"id":"2305.17934","title":"ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenes","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2508.17972","title":"SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization","created":"2025-08-25","cited_by_count":20,"area":null},{"id":"2505.04109","title":"One2Any: One-Reference 6D Pose Estimation for Any Object","created":"2025-05-07","cited_by_count":18,"area":null},{"id":"2312.06661","title":"UpFusion: Novel View Diffusion from Unposed Sparse View Observations","created":"2023-12-11","cited_by_count":14,"area":null},{"id":"2312.17250","title":"iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views","created":"2023-12-28","cited_by_count":14,"area":"diffusion"},{"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":"2403.03221","title":"FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation","created":"2024-03-05","cited_by_count":12,"area":null},{"id":"2411.16106","title":"UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image","created":"2024-11-25","cited_by_count":12,"area":null},{"id":"2310.03534","title":"3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2406.16384","title":"High-resolution open-vocabulary object 6D pose estimation","created":"2024-06-24","cited_by_count":10,"area":null},{"id":"2408.16690","title":"Generic Objects as Pose Probes for Few-shot View Synthesis","created":"2024-08-29","cited_by_count":9,"area":null},{"id":"2412.03570","title":"Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis","created":"2024-12-04","cited_by_count":9,"area":null},{"id":"2306.17140","title":"ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models","created":"2023-06-29","cited_by_count":8,"area":"diffusion"},{"id":"2507.14921","title":"Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction","created":"2025-07-20","cited_by_count":8,"area":null},{"id":"2403.14973","title":"Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularization","created":"2024-03-22","cited_by_count":7,"area":null},{"id":"2412.16155","title":"Can Generative Video Models Help Pose Estimation?","created":"2024-12-20","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":"2411.07096","title":"Extreme Rotation Estimation in the Wild","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2506.02112","title":"SAB3R: Semantic-Augmented Backbone in 3D Reconstruction","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2511.22686","title":"Emergent Extreme-View Geometry in 3D Foundation Models","created":"2025-11-27","cited_by_count":6,"area":null},{"id":"2404.03652","title":"The More You See in 2D, the More You Perceive in 3D","created":"2024-04-04","cited_by_count":5,"area":"diffusion"},{"id":"2407.08199","title":"SRPose: Two-view Relative Pose Estimation with Sparse Keypoints","created":"2024-07-11","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":"2402.02800","title":"Extreme Two-View Geometry From Object Poses with Diffusion Models","created":"2024-02-05","cited_by_count":4,"area":"diffusion"},{"id":"2410.18962","title":"Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2411.00543","title":"3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2510.18521","title":"RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation","created":"2025-10-21","cited_by_count":4,"area":null},{"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":"2408.09042","title":"ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation","created":"2024-08-16","cited_by_count":3,"area":null},{"id":"2503.18671","title":"Structure-Aware Correspondence Learning for Relative Pose Estimation","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2404.14280","title":"RESfM: Robust Deep Equivariant Structure from Motion","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2410.15636","title":"LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2412.08412","title":"Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Views","created":"2024-12-11","cited_by_count":2,"area":"diffusion"},{"id":"2503.21581","title":"AlignDiff: Learning Physically-Grounded Camera Alignment via Diffusion","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2507.01603","title":"DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation","created":"2025-07-02","cited_by_count":2,"area":"diffusion"},{"id":"2401.10886","title":"SCENES: Subpixel Correspondence Estimation With Epipolar Supervision","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2403.15272","title":"WSCLoc: Weakly-Supervised Sparse-View Camera Relocalization","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2404.02125","title":"3D Congealing: 3D-Aware Image Alignment in the Wild","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2411.15860","title":"Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching","created":"2024-11-24","cited_by_count":1,"area":null},{"id":"2504.00639","title":"Coca-Splat: Collaborative Optimization for Camera Parameters and 3D Gaussians","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2507.10265","title":"Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2602.04343","title":"Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.23951","title":"AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.26584","title":"Scene Grounding In the Wild","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2310.10051","title":"EAR-Net: Pursuing End-to-End Absolute Rotations from Multi-View Images","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2403.13683","title":"DVMNet++: Rethinking Relative Pose Estimation for Unseen Objects","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2406.18453","title":"Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Reference","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2503.03543","title":"A self-supervised cyclic neural-analytic approach for novel view synthesis and 3D reconstruction","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2503.22349","title":"GCRayDiffusion: Pose-Free Surface Reconstruction via Geometric Consistent Ray Diffusion","created":"2025-03-28","cited_by_count":0,"area":"diffusion"},{"id":"2505.01207","title":"T-Graph: Enhancing Sparse-view Camera Pose Estimation by Pairwise Translation Graph","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2506.01691","title":"SteerPose: Simultaneous Extrinsic Camera Calibration and Matching from Articulation","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2512.18784","title":"Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2601.13565","title":"Learning Fine-Grained Correspondence with Cross-Perspective Perception for Open-Vocabulary 6D Object Pose Estimation","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.06968","title":"Learning to Anchor Visual Odometry: KAN-Based Pose Regression for Planetary Landing","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2604.14762","title":"OmniGCD: Abstracting Generalized Category Discovery for Modality Agnosticism","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.07023","title":"Semantic Prior Guided One-View 6D Pose Estimation for Novel Objects","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.19865","title":"Landscape-Awareness for Geometric View Diffusion Model","created":"2026-05-19","cited_by_count":0,"area":"diffusion"},{"id":"2606.22076","title":"Learning Cross-View Semantic Priors for Single-Reference Unseen Object Pose Estimation","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.23634","title":"Pose Anything Anywhere:Model-free Object Poses from Arbitrary References","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2609.05210","title":"BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular Priors","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.32455","title":"QuacamFM: Quaternion-Constrained Flow Matching for Camera Pose Estimation","created":"2026-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2610.10960","title":"LVSPM: Long Sequence View Synthesis and Pose Estimation Model","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}