{"total":200,"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":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590,"area":null},{"id":"2112.10703","title":"Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs","created":"2021-12-20","cited_by_count":398,"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":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277,"area":null},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227,"area":null},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218,"area":null},{"id":"2406.12080","title":"A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets","created":"2024-06-17","cited_by_count":216,"area":null},{"id":"2208.04726","title":"Deep Patch Visual Odometry","created":"2022-08-08","cited_by_count":190,"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":"2202.00667","title":"DKM: Dense Kernelized Feature Matching for Geometry Estimation","created":"2022-02-01","cited_by_count":177,"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":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161,"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":"2203.09645","title":"MatchFormer: Interleaving Attention in Transformers for Feature Matching","created":"2022-03-17","cited_by_count":126,"area":null},{"id":"2403.04765","title":"Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed","created":"2024-03-07","cited_by_count":120,"area":null},{"id":"2301.07673","title":"OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models","created":"2023-01-18","cited_by_count":115,"area":null},{"id":"2507.16443","title":"VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences","created":"2025-07-22","cited_by_count":115,"area":null},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102,"area":null},{"id":"2412.09401","title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","created":"2024-12-12","cited_by_count":102,"area":null},{"id":"2210.10770","title":"LaMAR: Benchmarking Localization and Mapping for Augmented Reality","created":"2022-10-19","cited_by_count":100,"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":"2304.02009","title":"OrienterNet: Visual Localization in 2D Public Maps with Neural Matching","created":"2023-04-04","cited_by_count":84,"area":null},{"id":"2204.00559","title":"DFNet: Enhance Absolute Pose Regression with Direct Feature Matching","created":"2022-04-01","cited_by_count":82,"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":"2410.18956","title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","created":"2024-10-24","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":"2306.15669","title":"Detector-Free Structure from Motion","created":"2023-06-27","cited_by_count":71,"area":null},{"id":"2212.07766","title":"DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients","created":"2022-12-15","cited_by_count":60,"area":null},{"id":"2303.14478","title":"DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields","created":"2023-03-25","cited_by_count":60,"area":null},{"id":"2211.16991","title":"SparsePose: Sparse-View Camera Pose Regression and Refinement","created":"2022-11-29","cited_by_count":53,"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":"2412.09982","title":"SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video","created":"2024-12-13","cited_by_count":44,"area":null},{"id":"2502.07685","title":"Matrix3D: Large Photogrammetry Model All-in-One","created":"2025-02-11","cited_by_count":40,"area":null},{"id":"2303.17504","title":"3D Line Mapping Revisited","created":"2023-03-30","cited_by_count":39,"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":"2306.05407","title":"SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding","created":"2023-06-08","cited_by_count":38,"area":null},{"id":"2303.10087","title":"Neural Refinement for Absolute Pose Regression with Feature Synthesis","created":"2023-03-17","cited_by_count":37,"area":null},{"id":"2303.03003","title":"Efficient Large-scale Scene Representation with a Hybrid of High-resolution Grid and Plane Features","created":"2023-03-06","cited_by_count":36,"area":null},{"id":"2310.11475","title":"Tracking and Mapping in Medical Computer Vision: A Review","created":"2023-10-17","cited_by_count":36,"area":null},{"id":"2306.05410","title":"LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs","created":"2023-06-08","cited_by_count":33,"area":null},{"id":"2211.09682","title":"AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training","created":"2022-11-17","cited_by_count":31,"area":null},{"id":"2409.19811","title":"Robust Incremental Structure-from-Motion with Hybrid Features","created":"2024-09-29","cited_by_count":31,"area":null},{"id":"2305.15727","title":"POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference","created":"2023-05-25","cited_by_count":30,"area":null},{"id":"2312.09800","title":"Deep Event Visual Odometry","created":"2023-12-15","cited_by_count":29,"area":null},{"id":"2208.04307","title":"PlaneFormers: From Sparse View Planes to 3D Reconstruction","created":"2022-08-08","cited_by_count":26,"area":null},{"id":"2401.17592","title":"Local Feature Matching Using Deep Learning: A Survey","created":"2024-01-31","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":"2206.13850","title":"When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation","created":"2022-06-28","cited_by_count":24,"area":null},{"id":"2312.10649","title":"PNeRFLoc: Visual Localization with Point-based Neural Radiance Fields","created":"2023-12-17","cited_by_count":23,"area":null},{"id":"2211.16799","title":"NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction","created":"2022-11-30","cited_by_count":21,"area":null},{"id":"2302.12772","title":"FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking Datasets","created":"2023-02-24","cited_by_count":21,"area":null},{"id":"2308.09386","title":"DReg-NeRF: Deep Registration for Neural Radiance Fields","created":"2023-08-18","cited_by_count":21,"area":null},{"id":"2409.06685","title":"GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction","created":"2024-09-10","cited_by_count":20,"area":null},{"id":"2506.13750","title":"Test3R: Learning to Reconstruct 3D at Test Time","created":"2025-06-16","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":"2205.01694","title":"End2End Multi-View Feature Matching with Differentiable Pose Optimization","created":"2022-05-03","cited_by_count":19,"area":null},{"id":"2409.09479","title":"MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry","created":"2024-09-14","cited_by_count":19,"area":null},{"id":"2407.08561","title":"MapLocNet: Coarse-to-Fine Feature Registration for Visual Re-Localization in Navigation Maps","created":"2024-07-11","cited_by_count":18,"area":null},{"id":"2306.12547","title":"DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching","created":"2023-06-21","cited_by_count":17,"area":null},{"id":"2405.17705","title":"DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos","created":"2024-05-27","cited_by_count":16,"area":null},{"id":"2409.16502","title":"GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization","created":"2024-09-24","cited_by_count":16,"area":null},{"id":"2512.02541","title":"AVGGT: Rethinking Global Attention for Accelerating VGGT","created":"2025-12-02","cited_by_count":16,"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":"2203.06111","title":"Multi-sensor large-scale dataset for multi-view 3D reconstruction","created":"2022-03-11","cited_by_count":14,"area":null},{"id":"2305.09527","title":"Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares","created":"2023-05-16","cited_by_count":14,"area":null},{"id":"2503.08071","title":"GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats","created":"2025-03-11","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":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2211.12174","title":"The Monocular Depth Estimation Challenge","created":"2022-11-22","cited_by_count":13,"area":null},{"id":"2305.08810","title":"AutoRecon: Automated 3D Object Discovery and Reconstruction","created":"2023-05-15","cited_by_count":13,"area":null},{"id":"2407.11668","title":"Learning to Make Keypoints Sub-Pixel Accurate","created":"2024-07-16","cited_by_count":13,"area":null},{"id":"2112.04846","title":"ScaleNet: A Shallow Architecture for Scale Estimation","created":"2021-12-09","cited_by_count":12,"area":null},{"id":"2310.06984","title":"Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization","created":"2023-10-10","cited_by_count":12,"area":null},{"id":"2403.11460","title":"Fed3DGS: Scalable 3D Gaussian Splatting with Federated Learning","created":"2024-03-18","cited_by_count":12,"area":null},{"id":"2408.10739","title":"TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks","created":"2024-08-20","cited_by_count":12,"area":null},{"id":"2409.20563","title":"DressRecon: Freeform 4D Human Reconstruction from Monocular Video","created":"2024-09-30","cited_by_count":12,"area":null},{"id":"2501.13104","title":"Neural Radiance Fields for the Real World: A Survey","created":"2025-01-22","cited_by_count":12,"area":null},{"id":"2601.22615","title":"TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2211.15069","title":"FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network","created":"2022-11-28","cited_by_count":10,"area":null},{"id":"2304.14837","title":"IMP: Iterative Matching and Pose Estimation with Adaptive Pooling","created":"2023-04-28","cited_by_count":10,"area":null},{"id":"2310.16255","title":"UAV-Sim: NeRF-based Synthetic Data Generation for UAV-based Perception","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2504.06264","title":"D$^2$USt3R: Enhancing 3D Reconstruction for Dynamic Scenes","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2507.22052","title":"Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos","created":"2025-07-29","cited_by_count":10,"area":null},{"id":"2507.23569","title":"Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization","created":"2025-07-31","cited_by_count":10,"area":null},{"id":"2402.11141","title":"Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review","created":"2024-02-17","cited_by_count":9,"area":null},{"id":"2407.09285","title":"MetaFood CVPR 2024 Challenge on Physically Informed 3D Food Reconstruction: Methods and Results","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2501.01409","title":"JOG3R: Towards 3D-Consistent Video Generators","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2504.12356","title":"Regist3R: Incremental Registration with Stereo Foundation Model","created":"2025-04-16","cited_by_count":9,"area":null},{"id":"2309.06030","title":"Federated Learning for Large-Scale Scene Modeling with Neural Radiance Fields","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2311.18801","title":"Distributed Global Structure-from-Motion with a Deep Front-End","created":"2023-11-30","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":"2505.04612","title":"FastMap: Revisiting Structure from Motion through First-Order Optimization","created":"2025-05-07","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":"2605.26103","title":"Global Structure-from-Motion Meets Feedforward Reconstruction","created":"2026-05-25","cited_by_count":8,"area":null},{"id":"2303.15416","title":"3D Video Object Detection with Learnable Object-Centric Global Optimization","created":"2023-03-27","cited_by_count":7,"area":null},{"id":"2404.10887","title":"Grounded Language Agent for Product Search via Intelligent Web Interactions","created":"2024-04-16","cited_by_count":7,"area":"agents"}],"next_cursor":"100"}