{"total":152,"rows":[{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567,"area":null},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548,"area":null},{"id":"2312.02126","title":"SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM","created":"2023-12-04","cited_by_count":388,"area":null},{"id":"2104.14540","title":"The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth","created":"2021-04-29","cited_by_count":190,"area":null},{"id":"2210.13641","title":"NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields","created":"2022-10-24","cited_by_count":188,"area":null},{"id":"2304.14377","title":"Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM","created":"2023-04-27","cited_by_count":184,"area":null},{"id":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163,"area":null},{"id":"2211.11704","title":"ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields","created":"2022-11-21","cited_by_count":158,"area":null},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144,"area":null},{"id":"2309.02436","title":"GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction","created":"2023-09-05","cited_by_count":133,"area":null},{"id":"2210.05494","title":"Map-free Visual Relocalization: Metric Pose Relative to a Single Image","created":"2022-10-11","cited_by_count":114,"area":null},{"id":"2103.16525","title":"Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraints","created":"2021-03-30","cited_by_count":81,"area":null},{"id":"2402.13255","title":"How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Survey","created":"2024-02-20","cited_by_count":72,"area":null},{"id":"2105.11610","title":"Unsupervised Scale-consistent Depth Learning from Video","created":"2021-05-25","cited_by_count":69,"area":null},{"id":"2306.04633","title":"Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion","created":"2023-06-07","cited_by_count":64,"area":null},{"id":"2403.16095","title":"CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field","created":"2024-03-24","cited_by_count":61,"area":null},{"id":"2106.14386","title":"Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems","created":"2021-06-28","cited_by_count":54,"area":null},{"id":"2302.06556","title":"VA-DepthNet: A Variational Approach to Single Image Depth Prediction","created":"2023-02-13","cited_by_count":54,"area":null},{"id":"2108.01176","title":"Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks","created":"2021-08-02","cited_by_count":52,"area":null},{"id":"2309.10592","title":"NDDepth: Normal-Distance Assisted Monocular Depth Estimation","created":"2023-09-19","cited_by_count":45,"area":null},{"id":"2507.18255","title":"LONG3R: Long Sequence Streaming 3D Reconstruction","created":"2025-07-24","cited_by_count":45,"area":null},{"id":"2111.07418","title":"TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo","created":"2021-11-14","cited_by_count":39,"area":null},{"id":"2308.14713","title":"R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras","created":"2023-08-28","cited_by_count":39,"area":null},{"id":"2509.05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","created":"2025-09-05","cited_by_count":35,"area":null},{"id":"2105.07593","title":"Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation","created":"2021-05-17","cited_by_count":34,"area":null},{"id":"2202.09487","title":"SAGE: SLAM with Appearance and Geometry Prior for Endoscopy","created":"2022-02-19","cited_by_count":28,"area":null},{"id":"2309.09975","title":"GEDepth: Ground Embedding for Monocular Depth Estimation","created":"2023-09-18","cited_by_count":26,"area":null},{"id":"2404.06337","title":"Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences","created":"2024-04-09","cited_by_count":26,"area":null},{"id":"2411.17982","title":"HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction","created":"2024-11-27","cited_by_count":25,"area":null},{"id":"2103.00933","title":"DF-VO: What Should Be Learnt for Visual Odometry?","created":"2021-03-01","cited_by_count":22,"area":null},{"id":"2111.03098","title":"Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image","created":"2021-11-04","cited_by_count":20,"area":null},{"id":"2203.08122","title":"From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2302.03860","title":"EVEN: An Event-Based Framework for Monocular Depth Estimation at Adverse Night Conditions","created":"2023-02-08","cited_by_count":19,"area":null},{"id":"2303.03315","title":"MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision","created":"2023-03-06","cited_by_count":19,"area":null},{"id":"2407.20853","title":"NIS-SLAM: Neural Implicit Semantic RGB-D SLAM for 3D Consistent Scene Understanding","created":"2024-07-30","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":"2501.05446","title":"Relative Pose Estimation through Affine Corrections of Monocular Depth Priors","created":"2025-01-09","cited_by_count":18,"area":null},{"id":"2104.06789","title":"VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals","created":"2021-04-14","cited_by_count":17,"area":null},{"id":"2204.01268","title":"Improving Monocular Visual Odometry Using Learned Depth","created":"2022-04-04","cited_by_count":17,"area":null},{"id":"2209.15153","title":"MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priors","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2103.13684","title":"MBA-VO: Motion Blur Aware Visual Odometry","created":"2021-03-25","cited_by_count":16,"area":null},{"id":"2105.06143","title":"Boosting Light-Weight Depth Estimation Via Knowledge Distillation","created":"2021-05-13","cited_by_count":16,"area":"distill"},{"id":"2107.08994","title":"CodeMapping: Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations","created":"2021-07-19","cited_by_count":16,"area":null},{"id":"2202.02796","title":"GLPanoDepth: Global-to-Local Panoramic Depth Estimation","created":"2022-02-06","cited_by_count":16,"area":null},{"id":"2210.01276","title":"Probabilistic Volumetric Fusion for Dense Monocular SLAM","created":"2022-10-03","cited_by_count":16,"area":null},{"id":"2303.18164","title":"Single Image Depth Prediction Made Better: A Multivariate Gaussian Take","created":"2023-03-31","cited_by_count":14,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2308.14039","title":"Deep Learning for Visual Localization and Mapping: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2402.05869","title":"Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2212.06759","title":"Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2108.05246","title":"A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation of Indoor Scenes","created":"2021-08-11","cited_by_count":12,"area":null},{"id":"2212.08861","title":"DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Models","created":"2022-12-17","cited_by_count":12,"area":"diffusion"},{"id":"2303.04654","title":"Aberration-Aware Depth-from-Focus","created":"2023-03-08","cited_by_count":12,"area":null},{"id":"2308.03108","title":"SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation","created":"2023-08-06","cited_by_count":12,"area":null},{"id":"2511.23127","title":"DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation","created":"2025-11-28","cited_by_count":11,"area":"diffusion"},{"id":"2203.09737","title":"Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation","created":"2022-03-18","cited_by_count":10,"area":null},{"id":"2210.10491","title":"Visual SLAM: What are the Current Trends and What to Expect?","created":"2022-10-19","cited_by_count":10,"area":null},{"id":"2211.13551","title":"SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networks","created":"2022-11-24","cited_by_count":10,"area":null},{"id":"2303.01351","title":"APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigation","created":"2023-03-02","cited_by_count":10,"area":null},{"id":"2312.13471","title":"NeRF-VO: Real-Time Sparse Visual Odometry with Neural Radiance Fields","created":"2023-12-20","cited_by_count":10,"area":null},{"id":"2207.08794","title":"D$^3$FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance","created":"2022-07-18","cited_by_count":9,"area":null},{"id":"2311.07166","title":"NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion","created":"2023-11-13","cited_by_count":9,"area":null},{"id":"2504.02312","title":"OmniCam: Unified Multimodal Video Generation via Camera Control","created":"2025-04-03","cited_by_count":9,"area":null},{"id":"2103.10310","title":"Lighting Enhancement Aids Reconstruction of Colonoscopic Surfaces","created":"2021-03-18","cited_by_count":8,"area":null},{"id":"2108.07736","title":"A Hybrid Sparse-Dense Monocular SLAM System for Autonomous Driving","created":"2021-08-17","cited_by_count":8,"area":null},{"id":"2203.05712","title":"Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World","created":"2022-03-11","cited_by_count":8,"area":null},{"id":"2205.01656","title":"GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mapping","created":"2022-05-03","cited_by_count":8,"area":null},{"id":"2207.12244","title":"DeepFusion: Real-Time Dense 3D Reconstruction for Monocular SLAM using Single-View Depth and Gradient Predictions","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2209.05222","title":"A Review on Visual-SLAM: Advancements from Geometric Modelling to Learning-based Semantic Scene Understanding","created":"2022-09-12","cited_by_count":8,"area":null},{"id":"2210.02038","title":"MOTSLAM: MOT-assisted monocular dynamic SLAM using single-view depth estimation","created":"2022-10-05","cited_by_count":8,"area":null},{"id":"2602.05508","title":"VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency","created":"2026-02-05","cited_by_count":8,"area":null},{"id":"2109.03585","title":"Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes","created":"2021-09-08","cited_by_count":7,"area":null},{"id":"2209.06428","title":"Semantic Visual Simultaneous Localization and Mapping: A Survey","created":"2022-09-14","cited_by_count":7,"area":null},{"id":"2212.03499","title":"Learning Continuous Depth Representation via Geometric Spatial Aggregator","created":"2022-12-07","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":"2104.00431","title":"Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2503.21778","title":"HS-SLAM: Hybrid Representation with Structural Supervision for Improved Dense SLAM","created":"2025-03-27","cited_by_count":6,"area":null},{"id":"2507.19474","title":"DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representations","created":"2025-07-25","cited_by_count":6,"area":null},{"id":"2509.20757","title":"MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2509.23737","title":"GRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent State","created":"2025-09-28","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":"2103.06911","title":"CORSAIR: Convolutional Object Retrieval and Symmetry-AIded Registration","created":"2021-03-11","cited_by_count":5,"area":null},{"id":"2103.09071","title":"Map completion from partial observation using the global structure of multiple environmental maps","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2109.07339","title":"S3LAM: Structured Scene SLAM","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2305.05546","title":"ColonMapper: topological mapping and localization for colonoscopy","created":"2023-05-09","cited_by_count":5,"area":null},{"id":"2406.12671","title":"GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2510.00978","title":"A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2108.01654","title":"Comparison of modern open-source visual SLAM approaches","created":"2021-08-03","cited_by_count":4,"area":null},{"id":"2207.03539","title":"RWT-SLAM: Robust Visual SLAM for Highly Weak-textured Environments","created":"2022-07-07","cited_by_count":4,"area":null},{"id":"2208.02709","title":"Globally Consistent Video Depth and Pose Estimation with Efficient Test-Time Training","created":"2022-08-04","cited_by_count":4,"area":null},{"id":"2306.08648","title":"SimpleMapping: Real-Time Visual-Inertial Dense Mapping with Deep Multi-View Stereo","created":"2023-06-14","cited_by_count":4,"area":null},{"id":"2403.11515","title":"SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applications","created":"2024-03-18","cited_by_count":4,"area":null},{"id":"2407.02382","title":"Light-SLAM: A Robust Deep-Learning Visual SLAM System Based on LightGlue under Challenging Lighting Conditions","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2503.02955","title":"Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2604.06830","title":"VGGT-SLAM++","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2104.03109","title":"VGF-Net: Visual-Geometric Fusion Learning for Simultaneous Drone Navigation and Height Mapping","created":"2021-04-07","cited_by_count":3,"area":null},{"id":"2109.10077","title":"Scale-aware direct monocular odometry","created":"2021-09-21","cited_by_count":3,"area":null},{"id":"2203.02193","title":"Time-to-Label: Temporal Consistency for Self-Supervised Monocular 3D Object Detection","created":"2022-03-04","cited_by_count":3,"area":null},{"id":"2203.04538","title":"Monocular Depth Distribution Alignment with Low Computation","created":"2022-03-09","cited_by_count":3,"area":null},{"id":"2211.12600","title":"ArrayFlex: A Systolic Array Architecture with Configurable Transparent Pipelining","created":"2022-11-22","cited_by_count":3,"area":null}],"next_cursor":"100"}