{"list":"other","total":97,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"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":"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":"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":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"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":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"1905.03561","title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","created":"2019-05-09","cited_by_count":326},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302},{"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":"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":"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":"2012.09855","title":"Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image","created":"2020-12-17","cited_by_count":243},{"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":"1805.09817","title":"Stereo Magnification: Learning View Synthesis using Multiplane Images","created":"2018-05-24","cited_by_count":211},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"id":"2103.09213","title":"Back to the Feature: Learning Robust Camera Localization from Pixels to Pose","created":"2021-03-16","cited_by_count":199},{"id":"2408.13912","title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","created":"2024-08-25","cited_by_count":178},{"id":"1903.07504","title":"Understanding the Limitations of CNN-based Absolute Camera Pose Regression","created":"2019-03-18","cited_by_count":177},{"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":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166},{"id":"1712.03342","title":"Geometry-Aware Learning of Maps for Camera Localization","created":"2017-12-09","cited_by_count":161},{"id":"1912.05909","title":"MAGSAC++, a fast, reliable and accurate robust estimator","created":"2019-12-11","cited_by_count":161},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160},{"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":"1611.07890","title":"Image-based localization using LSTMs for structured feature correlation","created":"2016-11-23","cited_by_count":136},{"id":"1509.05909","title":"Modelling Uncertainty in Deep Learning for Camera Relocalization","created":"2015-09-19","cited_by_count":134},{"id":"1706.00984","title":"Graph-Cut RANSAC","created":"2017-06-03","cited_by_count":133},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"1803.07469","title":"MAGSAC: marginalizing sample consensus","created":"2018-03-20","cited_by_count":123},{"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":"1909.06216","title":"Hierarchical Scene Coordinate Classification and Regression for Visual Localization","created":"2019-09-13","cited_by_count":93},{"id":"1909.03557","title":"AtLoc: Attention Guided Camera Localization","created":"2019-09-08","cited_by_count":92},{"id":"2305.04926","title":"RelPose++: Recovering 6D Poses from Sparse-view Observations","created":"2023-05-08","cited_by_count":87},{"id":"2006.14616","title":"An Analysis of SVD for Deep Rotation Estimation","created":"2020-06-25","cited_by_count":86},{"id":"2204.00559","title":"DFNet: Enhance Absolute Pose Regression with Direct Feature Matching","created":"2022-04-01","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":"2007.13867","title":"Robust Image Retrieval-based Visual Localization using Kapture","created":"2020-07-27","cited_by_count":66},{"id":"1703.07971","title":"Image-based Localization using Hourglass Networks","created":"2017-03-23","cited_by_count":63},{"id":"2207.10762","title":"MeshLoc: Mesh-Based Visual Localization","created":"2022-07-21","cited_by_count":62},{"id":"1908.01293","title":"To Learn or Not to Learn: Visual Localization from Essential Matrices","created":"2019-08-04","cited_by_count":61},{"id":"2104.04073","title":"Direct-PoseNet: Absolute Pose Regression with Photometric Consistency","created":"2021-04-08","cited_by_count":61},{"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":"2208.06933","title":"Visual Localization via Few-Shot Scene Region Classification","created":"2022-08-14","cited_by_count":36},{"id":"1809.08402","title":"RPNet: an End-to-End Network for Relative Camera Pose Estimation","created":"2018-09-22","cited_by_count":31},{"id":"2409.19811","title":"Robust Incremental Structure-from-Motion with Hybrid Features","created":"2024-09-29","cited_by_count":31},{"id":"2103.16792","title":"Learning Camera Localization via Dense Scene Matching","created":"2021-03-31","cited_by_count":28},{"id":"1901.00643","title":"Baseline Desensitizing In Translation Averaging","created":"2019-01-03","cited_by_count":27},{"id":"2305.03595","title":"HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer","created":"2023-05-05","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":"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":"1811.04370","title":"Improved Visual Relocalization by Discovering Anchor Points","created":"2018-11-11","cited_by_count":16},{"id":"1802.03237","title":"Full-Frame Scene Coordinate Regression for Image-Based Localization","created":"2018-02-09","cited_by_count":13},{"id":"2403.03221","title":"FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation","created":"2024-03-05","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":"2108.03819","title":"DistillPose: Lightweight Camera Localization Using Auxiliary Learning","created":"2021-08-09","cited_by_count":10},{"id":"2402.08359","title":"Learning to Produce Semi-dense Correspondences for Visual Localization","created":"2024-02-13","cited_by_count":10},{"id":"2303.01743","title":"A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation","created":"2023-03-03","cited_by_count":9},{"id":"2307.09981","title":"Lazy Visual Localization via Motion Averaging","created":"2023-07-19","cited_by_count":8},{"id":"2211.14950","title":"Leveraging Image Matching Toward End-to-End Relative Camera Pose Regression","created":"2022-11-27","cited_by_count":6}],"next_cursor":null}