{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"1708.03852","title":"VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator","created":"2017-08-13","cited_by_count":423},{"id":"2012.05877","title":"INeRF: Inverting Neural Radiance Fields for Pose Estimation","created":"2020-12-10","cited_by_count":382},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302},{"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},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","cited_by_count":224},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"id":"2002.12324","title":"Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC","created":"2020-02-27","cited_by_count":176},{"id":"1712.03342","title":"Geometry-Aware Learning of Maps for Camera Localization","created":"2017-12-09","cited_by_count":161},{"id":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147},{"id":"1711.10228","title":"Learning Less is More - 6D Camera Localization via 3D Surface Regression","created":"2017-11-28","cited_by_count":146},{"id":"2503.01661","title":"MUSt3R: Multi-view Network for Stereo 3D Reconstruction","created":"2025-03-03","cited_by_count":141},{"id":"1611.07890","title":"Image-based localization using LSTMs for structured feature correlation","created":"2016-11-23","cited_by_count":136},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"2403.04765","title":"Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed","created":"2024-03-07","cited_by_count":120},{"id":"2110.06558","title":"LENS: Localization enhanced by NeRF synthesis","created":"2021-10-13","cited_by_count":117},{"id":"2210.05494","title":"Map-free Visual Relocalization: Metric Pose Relative to a Single Image","created":"2022-10-11","cited_by_count":114},{"id":"2103.11468","title":"Learning Multi-Scene Absolute Pose Regression with Transformers","created":"2021-03-21","cited_by_count":108},{"id":"2305.14059","title":"Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses","created":"2023-05-23","cited_by_count":107},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102},{"id":"2509.02560","title":"FastVGGT: Training-Free Acceleration of Visual Geometry Transformer","created":"2025-09-02","cited_by_count":98},{"id":"1909.06216","title":"Hierarchical Scene Coordinate Classification and Regression for Visual Localization","created":"2019-09-13","cited_by_count":93},{"id":"2305.04926","title":"RelPose++: Recovering 6D Poses from Sparse-view Observations","created":"2023-05-08","cited_by_count":87},{"id":"2204.00559","title":"DFNet: Enhance Absolute Pose Regression with Direct Feature Matching","created":"2022-04-01","cited_by_count":82},{"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},{"id":"1707.09733","title":"Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network","created":"2017-07-31","cited_by_count":79},{"id":"2312.09866","title":"PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment","created":"2023-12-15","cited_by_count":63},{"id":"1908.01293","title":"To Learn or Not to Learn: Visual Localization from Essential Matrices","created":"2019-08-04","cited_by_count":61},{"id":"1702.06521","title":"VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization","created":"2017-02-21","cited_by_count":58},{"id":"2409.14067","title":"SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality","created":"2024-09-21","cited_by_count":43},{"id":"2404.09884","title":"Map-Relative Pose Regression for Visual Re-Localization","created":"2024-04-15","cited_by_count":42},{"id":"2104.02538","title":"Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision","created":"2021-04-06","cited_by_count":37},{"id":"2303.10087","title":"Neural Refinement for Absolute Pose Regression with Feature Synthesis","created":"2023-03-17","cited_by_count":37},{"id":"2403.20034","title":"NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising","created":"2024-03-29","cited_by_count":30},{"id":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29},{"id":"1908.04391","title":"Local Supports Global: Deep Camera Relocalization with Sequence Enhancement","created":"2019-08-06","cited_by_count":25},{"id":"2405.20031","title":"MG-SLAM: Structure Gaussian Splatting SLAM with Manhattan World Hypothesis","created":"2024-05-30","cited_by_count":22},{"id":"2011.04539","title":"Learning to Localize in New Environments from Synthetic Training Data","created":"2020-11-09","cited_by_count":21},{"id":"1811.04370","title":"Improved Visual Relocalization by Discovering Anchor Points","created":"2018-11-11","cited_by_count":16},{"id":"2404.06050","title":"Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes","created":"2024-04-09","cited_by_count":15},{"id":"2505.18992","title":"VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenes","created":"2025-05-25","cited_by_count":13},{"id":"2310.06984","title":"Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization","created":"2023-10-10","cited_by_count":12},{"id":"2308.11783","title":"Coarse-to-Fine Multi-Scene Pose Regression with Transformers","created":"2023-08-22","cited_by_count":11},{"id":"2403.12800","title":"Learning Neural Volumetric Pose Features for Camera Localization","created":"2024-03-19","cited_by_count":11},{"id":"2506.18678","title":"MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representation","created":"2025-06-23","cited_by_count":11},{"id":"2512.21078","title":"UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer","created":"2025-12-24","cited_by_count":8},{"id":"2507.11001","title":"Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based Adaptation","created":"2025-07-15","cited_by_count":6},{"id":"2509.23737","title":"GRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent State","created":"2025-09-28","cited_by_count":6},{"id":"2507.12194","title":"UniLGL: Learning Uniform Place Recognition for FOV-limited/Panoramic LiDAR Global Localization","created":"2025-07-16","cited_by_count":4}],"next_cursor":null}