{"list":"other","total":94,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"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":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"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":"2104.06405","title":"BARF: Bundle-Adjusting Neural Radiance Fields","created":"2021-04-13","cited_by_count":642},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2012.05877","title":"INeRF: Inverting Neural Radiance Fields for Pose Estimation","created":"2020-12-10","cited_by_count":382},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"1611.05705","title":"DSAC - Differentiable RANSAC for Camera Localization","created":"2016-11-17","cited_by_count":266},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","cited_by_count":224},{"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":"1812.04072","title":"PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image","created":"2018-12-10","cited_by_count":105},{"id":"2210.10770","title":"LaMAR: Benchmarking Localization and Mapping for Augmented Reality","created":"2022-10-19","cited_by_count":100},{"id":"2106.02795","title":"Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding","created":"2021-06-05","cited_by_count":93},{"id":"2308.03768","title":"GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer","created":"2023-07-25","cited_by_count":84},{"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":"1804.06278","title":"PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image","created":"2018-04-17","cited_by_count":77},{"id":"1908.02484","title":"Expert Sample Consensus Applied to Camera Re-Localization","created":"2019-08-07","cited_by_count":70},{"id":"2304.02008","title":"GlueStick: Robust Image Matching by Sticking Points and Lines Together","created":"2023-04-04","cited_by_count":66},{"id":"1603.05772","title":"Learning to Navigate the Energy Landscape","created":"2016-03-18","cited_by_count":62},{"id":"2207.10762","title":"MeshLoc: Mesh-Based Visual Localization","created":"2022-07-21","cited_by_count":62},{"id":"1902.09777","title":"Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding","created":"2019-02-26","cited_by_count":56},{"id":"1712.05773","title":"Semantic Visual Localization","created":"2017-12-15","cited_by_count":54},{"id":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50},{"id":"2203.12979","title":"Is Geometry Enough for Matching in Visual Localization?","created":"2022-03-24","cited_by_count":48},{"id":"2303.04869","title":"CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation","created":"2023-03-08","cited_by_count":45},{"id":"2409.14067","title":"SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality","created":"2024-09-21","cited_by_count":43},{"id":"2501.07556","title":"MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training","created":"2025-01-13","cited_by_count":41},{"id":"1807.07512","title":"Hybrid Scene Compression for Visual Localization","created":"2018-07-19","cited_by_count":40},{"id":"2103.12032","title":"Tangent Space Backpropagation for 3D Transformation Groups","created":"2021-03-22","cited_by_count":40},{"id":"2103.14644","title":"Planar Surface Reconstruction from Sparse Views","created":"2021-03-26","cited_by_count":40},{"id":"2303.17504","title":"3D Line Mapping Revisited","created":"2023-03-30","cited_by_count":39},{"id":"2007.14628","title":"Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization","created":"2020-07-29","cited_by_count":38},{"id":"2208.06933","title":"Visual Localization via Few-Shot Scene Region Classification","created":"2022-08-14","cited_by_count":36},{"id":"2107.13108","title":"PlaneTR: Structure-Guided Transformers for 3D Plane Recovery","created":"2021-07-27","cited_by_count":33},{"id":"2403.09577","title":"The NeRFect Match: Exploring NeRF Features for Visual Localization","created":"2024-03-14","cited_by_count":32},{"id":"2310.03420","title":"FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators","created":"2023-10-05","cited_by_count":31},{"id":"2408.11085","title":"GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting","created":"2024-08-20","cited_by_count":31},{"id":"2304.14880","title":"SGAligner : 3D Scene Alignment with Scene Graphs","created":"2023-04-28","cited_by_count":30},{"id":"2104.09169","title":"LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments","created":"2021-04-19","cited_by_count":29},{"id":"2203.12082","title":"PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo","created":"2022-03-22","cited_by_count":29},{"id":"2404.00469","title":"SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs","created":"2024-03-30","cited_by_count":29},{"id":"2206.07710","title":"PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos","created":"2022-06-15","cited_by_count":27},{"id":"2308.05667","title":"2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds","created":"2023-08-10","cited_by_count":27},{"id":"2312.10649","title":"PNeRFLoc: Visual Localization with Point-based Neural Radiance Fields","created":"2023-12-17","cited_by_count":23},{"id":"2202.12197","title":"Situational Graphs for Robot Navigation in Structured Indoor Environments","created":"2022-02-24","cited_by_count":21},{"id":"2211.16799","title":"NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction","created":"2022-11-30","cited_by_count":21},{"id":"2304.05947","title":"Visual Localization using Imperfect 3D Models from the Internet","created":"2023-04-12","cited_by_count":20},{"id":"2402.02352","title":"Region-Based Representations Revisited","created":"2024-02-04","cited_by_count":18},{"id":"2403.03370","title":"F$^3$Loc: Fusion and Filtering for Floorplan Localization","created":"2024-03-05","cited_by_count":18},{"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},{"id":"2501.01421","title":"R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization","created":"2025-01-02","cited_by_count":17},{"id":"2503.19358","title":"From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting","created":"2025-03-25","cited_by_count":14},{"id":"2406.08960","title":"AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings","created":"2024-06-13","cited_by_count":13},{"id":"2412.03451","title":"PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes","created":"2024-12-04","cited_by_count":13},{"id":"2502.15011","title":"CrossOver: 3D Scene Cross-Modal Alignment","created":"2025-02-20","cited_by_count":12},{"id":"2312.05889","title":"SuperPrimitive: Scene Reconstruction at a Primitive Level","created":"2023-12-10","cited_by_count":11},{"id":"2412.01826","title":"RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations","created":"2024-12-02","cited_by_count":11},{"id":"2507.09291","title":"Supercharging Floorplan Localization with Semantic Rays","created":"2025-07-12","cited_by_count":11},{"id":"2507.23569","title":"Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization","created":"2025-07-31","cited_by_count":10},{"id":"2407.10439","title":"PolyRoom: Room-aware Transformer for Floorplan Reconstruction","created":"2024-07-15","cited_by_count":9},{"id":"2410.11187","title":"Multiview Scene Graph","created":"2024-10-15","cited_by_count":9},{"id":"1803.08407","title":"PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction","created":"2018-03-22","cited_by_count":8},{"id":"2507.06651","title":"Diff$^2$I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Prior","created":"2025-07-09","cited_by_count":8},{"id":"2001.07360","title":"From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds","created":"2020-01-21","cited_by_count":7},{"id":"2307.13756","title":"PlaneRecTR++: Unified Query Learning for Joint 3D Planar Reconstruction and Pose Estimation","created":"2023-07-25","cited_by_count":6},{"id":"2411.19950","title":"AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos","created":"2024-11-29","cited_by_count":6},{"id":"2506.02493","title":"Towards In-the-wild 3D Plane Reconstruction from a Single Image","created":"2025-06-03","cited_by_count":6},{"id":"2401.00871","title":"PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields","created":"2023-12-30","cited_by_count":5},{"id":"2404.10527","title":"SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments","created":"2024-04-16","cited_by_count":5},{"id":"2507.00659","title":"LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment","created":"2025-07-01","cited_by_count":5},{"id":"2510.18714","title":"PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting","created":"2025-10-21","cited_by_count":5},{"id":"2502.20036","title":"A2-GNN: Angle-Annular GNN for Visual Descriptor-free Camera Relocalization","created":"2025-02-27","cited_by_count":3},{"id":"2508.20981","title":"ActLoc: Learning to Localize on the Move via Active Viewpoint Selection","created":"2025-08-28","cited_by_count":2},{"id":"2404.16552","title":"Efficient Solution of Point-Line Absolute Pose","created":"2024-04-25","cited_by_count":1}],"next_cursor":null}