{"list":"other","total":56,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"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":"2203.09517","title":"TensoRF: Tensorial Radiance Fields","created":"2022-03-17","cited_by_count":1280},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"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":"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":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"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":"2006.13566","title":"DISK: Learning local features with policy gradient","created":"2020-06-24","cited_by_count":312},{"id":"1603.09114","title":"LIFT: Learned Invariant Feature Transform","created":"2016-03-30","cited_by_count":306},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"1611.05705","title":"DSAC - Differentiable RANSAC for Camera Localization","created":"2016-11-17","cited_by_count":266},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"2003.01587","title":"Image Matching across Wide Baselines: From Paper to Practice","created":"2020-03-03","cited_by_count":225},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"2103.14167","title":"COTR: Correspondence Transformer for Matching Across Images","created":"2021-03-25","cited_by_count":183},{"id":"1911.11130","title":"Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild","created":"2019-11-25","cited_by_count":180},{"id":"1806.04807","title":"BA-Net: Dense Bundle Adjustment Network","created":"2018-06-13","cited_by_count":175},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171},{"id":"1701.08493","title":"A Survey of Structure from Motion","created":"2017-01-30","cited_by_count":158},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147},{"id":"1905.04132","title":"Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses","created":"2019-05-10","cited_by_count":129},{"id":"2203.09645","title":"MatchFormer: Interleaving Attention in Transformers for Feature Matching","created":"2022-03-17","cited_by_count":126},{"id":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102},{"id":"2108.08771","title":"Learning to Match Features with Seeded Graph Matching Network","created":"2021-08-19","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":"2306.15669","title":"Detector-Free Structure from Motion","created":"2023-06-27","cited_by_count":71},{"id":"1912.09697","title":"DeepSFM: Structure From Motion Via Deep Bundle Adjustment","created":"2019-12-20","cited_by_count":70},{"id":"2207.09442","title":"Theseus: A Library for Differentiable Nonlinear Optimization","created":"2022-07-19","cited_by_count":65},{"id":"2204.11700","title":"ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching","created":"2022-04-25","cited_by_count":62},{"id":"2211.16991","title":"SparsePose: Sparse-View Camera Pose Regression and Refinement","created":"2022-11-29","cited_by_count":53},{"id":"2212.04492","title":"Few-View Object Reconstruction with Unknown Categories and Camera Poses","created":"2022-12-08","cited_by_count":53},{"id":"1412.0165","title":"Robust Camera Location Estimation by Convex Programming","created":"2014-11-29","cited_by_count":41},{"id":"2104.00556","title":"Deep Two-View Structure-from-Motion Revisited","created":"2021-04-01","cited_by_count":39},{"id":"2212.13185","title":"Generalized Differentiable RANSAC","created":"2022-12-26","cited_by_count":30},{"id":"1705.03951","title":"Learning 3D Object Categories by Looking Around Them","created":"2017-05-10","cited_by_count":26},{"id":"2206.08365","title":"Virtual Correspondence: Humans as a Cue for Extreme-View Geometry","created":"2022-06-16","cited_by_count":25},{"id":"2003.08348","title":"Multi-View Optimization of Local Feature Geometry","created":"2020-03-18","cited_by_count":24},{"id":"2308.15984","title":"Learning Structure-from-Motion with Graph Attention Networks","created":"2023-08-30","cited_by_count":10},{"id":"1503.01832","title":"Linear Global Translation Estimation with Feature Tracks","created":"2015-03-06","cited_by_count":9}],"next_cursor":null}