{"total":150,"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":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227,"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":"2412.06974","title":"MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds","created":"2024-12-09","cited_by_count":141,"area":null},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87,"area":null},{"id":"2208.07227","title":"DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images","created":"2022-08-15","cited_by_count":69,"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":"2103.12957","title":"Multi-view 3D Reconstruction with Transformer","created":"2021-03-24","cited_by_count":52,"area":null},{"id":"2104.13530","title":"Extreme Rotation Estimation using Dense Correlation Volumes","created":"2021-04-28","cited_by_count":42,"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":"2105.08941","title":"Large-scale Localization Datasets in Crowded Indoor Spaces","created":"2021-05-19","cited_by_count":29,"area":null},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2106.12102","title":"LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction","created":"2021-06-23","cited_by_count":25,"area":null},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","cited_by_count":25,"area":null},{"id":"2103.12209","title":"Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision","created":"2021-03-22","cited_by_count":24,"area":null},{"id":"2402.14253","title":"MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion","created":"2024-02-22","cited_by_count":22,"area":null},{"id":"2209.11945","title":"Towards Bridging the Space Domain Gap for Satellite Pose Estimation using Event Sensing","created":"2022-09-24","cited_by_count":21,"area":null},{"id":"2403.09079","title":"PreSight: Enhancing Autonomous Vehicle Perception with City-Scale NeRF Priors","created":"2024-03-14","cited_by_count":21,"area":null},{"id":"2306.11368","title":"RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation","created":"2023-06-20","cited_by_count":20,"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":"2203.13185","title":"Quantum Motion Segmentation","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2204.09138","title":"RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds","created":"2022-04-19","cited_by_count":16,"area":null},{"id":"2210.02009","title":"Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation","created":"2022-10-05","cited_by_count":16,"area":null},{"id":"2104.06703","title":"Deep Permutation Equivariant Structure from Motion","created":"2021-04-14","cited_by_count":15,"area":null},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2309.02102","title":"Iterative Superquadric Recomposition of 3D Objects from Multiple Views","created":"2023-09-05","cited_by_count":13,"area":null},{"id":"2403.11789","title":"EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encoding","created":"2024-03-18","cited_by_count":13,"area":null},{"id":"2507.06230","title":"Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion","created":"2025-07-08","cited_by_count":13,"area":null},{"id":"2207.10156","title":"Structural Causal 3D Reconstruction","created":"2022-07-20","cited_by_count":12,"area":null},{"id":"2310.19629","title":"RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency","created":"2023-10-30","cited_by_count":12,"area":null},{"id":"2404.00714","title":"Neural Radiance Field-based Visual Rendering: A Comprehensive Review","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2405.16788","title":"3D Reconstruction with Fast Dipole Sums","created":"2024-05-27","cited_by_count":12,"area":null},{"id":"2411.11934","title":"SpatialDreamer: Self-supervised Stereo Video Synthesis from Monocular Input","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2310.09776","title":"CBARF: Cascaded Bundle-Adjusting Neural Radiance Fields from Imperfect Camera Poses","created":"2023-10-15","cited_by_count":11,"area":null},{"id":"2401.09252","title":"3D Scene Geometry Estimation from 360$^\\circ$ Imagery: A Survey","created":"2024-01-17","cited_by_count":11,"area":null},{"id":"2412.01543","title":"6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting","created":"2024-12-02","cited_by_count":11,"area":null},{"id":"2512.19949","title":"How Much 3D Do Video Foundation Models Encode?","created":"2025-12-23","cited_by_count":11,"area":null},{"id":"2112.14651","title":"On the Instability of Relative Pose Estimation and RANSAC's Role","created":"2021-12-29","cited_by_count":10,"area":null},{"id":"2210.11419","title":"GPR-Net: Multi-view Layout Estimation via a Geometry-aware Panorama Registration Network","created":"2022-10-20","cited_by_count":10,"area":null},{"id":"2212.07211","title":"RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging","created":"2022-12-14","cited_by_count":10,"area":null},{"id":"2105.09847","title":"M4Depth: Monocular depth estimation for autonomous vehicles in unseen environments","created":"2021-05-20","cited_by_count":9,"area":null},{"id":"2210.11443","title":"Snapshot of Algebraic Vision","created":"2022-10-20","cited_by_count":9,"area":null},{"id":"2309.07471","title":"EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2211.02299","title":"GARNet: Global-Aware Multi-View 3D Reconstruction Network and the Cost-Performance Tradeoff","created":"2022-11-04","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":"2302.13987","title":"UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D Reconstruction","created":"2023-02-27","cited_by_count":7,"area":null},{"id":"2305.05268","title":"Rotation Synchronization via Deep Matrix Factorization","created":"2023-05-09","cited_by_count":7,"area":null},{"id":"2308.10337","title":"Strata-NeRF : Neural Radiance Fields for Stratified Scenes","created":"2023-08-20","cited_by_count":7,"area":null},{"id":"2308.10705","title":"Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modeling","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2309.11993","title":"Neural Stochastic Screened Poisson Reconstruction","created":"2023-09-21","cited_by_count":7,"area":null},{"id":"2410.03592","title":"Variational Bayes Gaussian Splatting","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2201.04797","title":"Scalable Cluster-Consistency Statistics for Robust Multi-Object Matching","created":"2022-01-13","cited_by_count":6,"area":null},{"id":"2211.14950","title":"Leveraging Image Matching Toward End-to-End Relative Camera Pose Regression","created":"2022-11-27","cited_by_count":6,"area":null},{"id":"2307.03704","title":"Equivariant Single View Pose Prediction Via Induced and Restricted Representations","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2411.07096","title":"Extreme Rotation Estimation in the Wild","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2108.05615","title":"DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes","created":"2021-08-12","cited_by_count":5,"area":null},{"id":"2112.05598","title":"PERF: Performant, Explicit Radiance Fields","created":"2021-12-10","cited_by_count":5,"area":null},{"id":"2205.14575","title":"3D-C2FT: Coarse-to-fine Transformer for Multi-view 3D Reconstruction","created":"2022-05-29","cited_by_count":5,"area":null},{"id":"2303.17094","title":"Enhanced Stable View Synthesis","created":"2023-03-30","cited_by_count":5,"area":null},{"id":"2308.08724","title":"Long-Range Grouping Transformer for Multi-View 3D Reconstruction","created":"2023-08-17","cited_by_count":5,"area":null},{"id":"2405.14342","title":"RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2508.08094","title":"3D Plant Root Skeleton Detection and Extraction","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2303.08096","title":"MELON: NeRF with Unposed Images in SO(3)","created":"2023-03-14","cited_by_count":4,"area":null},{"id":"2501.01677","title":"PG-SAG: Parallel Gaussian Splatting for Fine-Grained Large-Scale Urban Buildings Reconstruction via Semantic-Aware Grouping","created":"2025-01-03","cited_by_count":4,"area":null},{"id":"2203.07553","title":"VPFusion: Joint 3D Volume and Pixel-Aligned Feature Fusion for Single and Multi-view 3D Reconstruction","created":"2022-03-14","cited_by_count":3,"area":null},{"id":"2402.04554","title":"BirdNeRF: Fast Neural Reconstruction of Large-Scale Scenes From Aerial Imagery","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2405.06216","title":"Event-based Structure-from-Orbit","created":"2024-05-10","cited_by_count":3,"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":"2409.09313","title":"Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor","created":"2024-09-14","cited_by_count":3,"area":null},{"id":"2504.11202","title":"Focal Split: Untethered Snapshot Depth from Differential Defocus","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2511.02329","title":"Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization","created":"2025-11-04","cited_by_count":3,"area":null},{"id":"2602.00865","title":"Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2603.02351","title":"MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2103.07570","title":"Dilated Fully Convolutional Neural Network for Depth Estimation from a Single Image","created":"2021-03-12","cited_by_count":2,"area":null},{"id":"2109.12131","title":"Automatic Map Update Using Dashcam Videos","created":"2021-09-24","cited_by_count":2,"area":null},{"id":"2203.01553","title":"Addressing the Shape-Radiance Ambiguity in View-Dependent Radiance Fields","created":"2022-03-03","cited_by_count":2,"area":null},{"id":"2310.00783","title":"Propagating Semantic Labels in Video Data","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2401.13357","title":"Linear Relative Pose Estimation Founded on Pose-only Imaging Geometry","created":"2024-01-24","cited_by_count":2,"area":null},{"id":"2404.14280","title":"RESfM: Robust Deep Equivariant Structure from Motion","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2405.07027","title":"TD-NeRF: Novel Truncated Depth Prior for Joint Camera Pose and Neural Radiance Field Optimization","created":"2024-05-11","cited_by_count":2,"area":null},{"id":"2406.19390","title":"SALVe: Semantic Alignment Verification for Floorplan Reconstruction from Sparse Panoramas","created":"2024-06-27","cited_by_count":2,"area":null},{"id":"2410.18987","title":"Point Cloud Synthesis Using Inner Product Transforms","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2411.07430","title":"XPoint: A Self-Supervised Visual-State-Space based Architecture for Multispectral Image Registration","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2412.10308","title":"TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2505.15814","title":"A Taxonomy of Structure from Motion Methods","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2509.26621","title":"HART: Human Aligned Reconstruction Transformer","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.26443","title":"PointSt3R: Point Tracking through 3D Grounded Correspondence","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2602.22096","title":"WeatherCity: Urban Scene Reconstruction with Controllable Multi-Weather Transformation","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2604.07372","title":"NS-RGS: Newton-Schulz based Riemannian gradient method for orthogonal group synchronization","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2607.14481","title":"Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2106.15493","title":"Generalized Orthogonal Procrustes Problem under Arbitrary Adversaries","created":"2021-06-29","cited_by_count":1,"area":null},{"id":"2108.09047","title":"AutoLay: Benchmarking amodal layout estimation for autonomous driving","created":"2021-08-20","cited_by_count":1,"area":null},{"id":"2108.10972","title":"Domain Adaptation for Real-World Single View 3D Reconstruction","created":"2021-08-24","cited_by_count":1,"area":null},{"id":"2207.09418","title":"Unrolled algorithms for group synchronization","created":"2022-07-19","cited_by_count":1,"area":null},{"id":"2308.01246","title":"Tirtha -- An Automated Platform to Crowdsource Images and Create 3D Models of Heritage Sites","created":"2023-08-02","cited_by_count":1,"area":null},{"id":"2310.02719","title":"Condition numbers in multiview geometry, instability in relative pose estimation, and RANSAC","created":"2023-10-04","cited_by_count":1,"area":null},{"id":"2310.09632","title":"Time-based Mapping of Space Using Visual Motion Invariants","created":"2023-10-14","cited_by_count":1,"area":null}],"next_cursor":"100"}