{"list":"other","total":68,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"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":"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":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"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":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367},{"id":"2106.02634","title":"Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering","created":"2021-06-04","cited_by_count":332},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277},{"id":"1611.05705","title":"DSAC - Differentiable RANSAC for Camera Localization","created":"2016-11-17","cited_by_count":266},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","cited_by_count":224},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"1906.07589","title":"Learning with Average Precision: Training Image Retrieval with a Listwise Loss","created":"2019-06-18","cited_by_count":185},{"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":"2409.19152","title":"MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion","created":"2024-09-27","cited_by_count":162},{"id":"1912.05909","title":"MAGSAC++, a fast, reliable and accurate robust estimator","created":"2019-12-11","cited_by_count":161},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"1704.03489","title":"CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction","created":"2017-04-11","cited_by_count":152},{"id":"1803.07469","title":"MAGSAC: marginalizing sample consensus","created":"2018-03-20","cited_by_count":123},{"id":"2304.03608","title":"ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation","created":"2023-04-07","cited_by_count":121},{"id":"2403.04765","title":"Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed","created":"2024-03-07","cited_by_count":120},{"id":"1904.00889","title":"Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters","created":"2019-04-01","cited_by_count":118},{"id":"2401.12592","title":"RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos","created":"2024-01-23","cited_by_count":115},{"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":"1909.06216","title":"Hierarchical Scene Coordinate Classification and Regression for Visual Localization","created":"2019-09-13","cited_by_count":93},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","cited_by_count":89},{"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":"2203.10157","title":"ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers","created":"2022-03-18","cited_by_count":70},{"id":"2007.13867","title":"Robust Image Retrieval-based Visual Localization using Kapture","created":"2020-07-27","cited_by_count":66},{"id":"1908.01293","title":"To Learn or Not to Learn: Visual Localization from Essential Matrices","created":"2019-08-04","cited_by_count":61},{"id":"2406.04340","title":"GLACE: Global Local Accelerated Coordinate Encoding","created":"2024-06-06","cited_by_count":48},{"id":"2501.14914","title":"Light3R-SfM: Towards Feed-forward Structure-from-Motion","created":"2025-01-24","cited_by_count":47},{"id":"2404.09884","title":"Map-Relative Pose Regression for Visual Re-Localization","created":"2024-04-15","cited_by_count":42},{"id":"1702.02779","title":"On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation","created":"2017-02-09","cited_by_count":38},{"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":"2208.06933","title":"Visual Localization via Few-Shot Scene Region Classification","created":"2022-08-14","cited_by_count":36},{"id":"1810.12163","title":"Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade","created":"2018-10-29","cited_by_count":35},{"id":"2005.13605","title":"D2D: Keypoint Extraction with Describe to Detect Approach","created":"2020-05-27","cited_by_count":34},{"id":"2008.02004","title":"Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes","created":"2020-08-05","cited_by_count":31},{"id":"1906.08744","title":"Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation","created":"2019-06-20","cited_by_count":28},{"id":"2211.11177","title":"NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization","created":"2022-11-21","cited_by_count":26},{"id":"2404.06337","title":"Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences","created":"2024-04-09","cited_by_count":26},{"id":"2011.04539","title":"Learning to Localize in New Environments from Synthetic Training Data","created":"2020-11-09","cited_by_count":21},{"id":"2005.05777","title":"HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learning","created":"2020-05-12","cited_by_count":13},{"id":"2103.06535","title":"Calibrated and Partially Calibrated Semi-Generalized Homographies","created":"2021-03-11","cited_by_count":12},{"id":"2112.04846","title":"ScaleNet: A Shallow Architecture for Scale Estimation","created":"2021-12-09","cited_by_count":12},{"id":"2501.18804","title":"Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion","created":"2025-01-30","cited_by_count":12},{"id":"2306.01596","title":"Two-View Geometry Scoring Without Correspondences","created":"2023-06-02","cited_by_count":11},{"id":"2504.17636","title":"A Guide to Structureless Visual Localization","created":"2025-04-24","cited_by_count":9},{"id":"2409.14269","title":"Combining Absolute and Semi-Generalized Relative Poses for Visual Localization","created":"2024-09-21","cited_by_count":4}],"next_cursor":null}