{"list":"other","total":81,"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":"2304.07193","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":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"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":"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":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"2007.11898","title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM","created":"2020-07-23","cited_by_count":878},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"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":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"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":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"1704.05939","title":"HPatches: A benchmark and evaluation of handcrafted and learned local descriptors","created":"2017-04-19","cited_by_count":264},{"id":"2003.01587","title":"Image Matching across Wide Baselines: From Paper to Practice","created":"2020-03-03","cited_by_count":225},{"id":"2104.02409","title":"Learning to Estimate Hidden Motions with Global Motion Aggregation","created":"2021-04-06","cited_by_count":224},{"id":"1906.06195","title":"R2D2: Repeatable and Reliable Detector and Descriptor","created":"2019-06-14","cited_by_count":207},{"id":"2012.01411","title":"PatchmatchNet: Learned Multi-View Patchmatch Stereo","created":"2020-12-02","cited_by_count":207},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"id":"2103.14167","title":"COTR: Correspondence Transformer for Matching Across Images","created":"2021-03-25","cited_by_count":183},{"id":"2202.00667","title":"DKM: Dense Kernelized Feature Matching for Geometry Estimation","created":"2022-02-01","cited_by_count":177},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171},{"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":"1701.08493","title":"A Survey of Structure from Motion","created":"2017-01-30","cited_by_count":158},{"id":"1912.08329","title":"Cost Volume Pyramid Based Depth Inference for Multi-View Stereo","created":"2019-12-18","cited_by_count":154},{"id":"1911.12012","title":"Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness","created":"2019-11-27","cited_by_count":151},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147},{"id":"1912.05524","title":"GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences","created":"2019-12-11","cited_by_count":139},{"id":"1904.05019","title":"SOSNet: Second Order Similarity Regularization for Local Descriptor Learning","created":"2019-04-10","cited_by_count":131},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"2003.10071","title":"ASLFeat: Learning Local Features of Accurate Shape and Localization","created":"2020-03-23","cited_by_count":130},{"id":"2012.01909","title":"Patch2Pix: Epipolar-Guided Pixel-Level Correspondences","created":"2020-12-03","cited_by_count":129},{"id":"2201.02767","title":"QuadTree Attention for Vision Transformers","created":"2022-01-08","cited_by_count":129},{"id":"2104.03866","title":"SMD-Nets: Stereo Mixture Density Networks","created":"2021-04-08","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":"2005.04551","title":"Epipolar Transformers","created":"2020-05-10","cited_by_count":117},{"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":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114},{"id":"2101.01710","title":"Learning Accurate Dense Correspondences and When to Trust Them","created":"2021-01-05","cited_by_count":113},{"id":"2004.13324","title":"Learning Feature Descriptors using Camera Pose Supervision","created":"2020-04-28","cited_by_count":104},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102},{"id":"2305.04926","title":"RelPose++: Recovering 6D Poses from Sparse-view Observations","created":"2023-05-08","cited_by_count":87},{"id":"1501.02565","title":"EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow","created":"2015-01-12","cited_by_count":80},{"id":"2109.13912","title":"PDC-Net+: Enhanced Probabilistic Dense Correspondence Network","created":"2021-09-28","cited_by_count":80},{"id":"1810.08393","title":"DGC-Net: Dense Geometric Correspondence Network","created":"2018-10-19","cited_by_count":67},{"id":"2007.13867","title":"Robust Image Retrieval-based Visual Localization using Kapture","created":"2020-07-27","cited_by_count":66},{"id":"1912.11746","title":"Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume","created":"2019-12-26","cited_by_count":59},{"id":"1711.06704","title":"Repeatability Is Not Enough: Learning Affine Regions via Discriminability","created":"2017-11-17","cited_by_count":57},{"id":"1411.4568","title":"TILDE: A Temporally Invariant Learned DEtector","created":"2014-11-17","cited_by_count":55},{"id":"2205.04502","title":"Multiview Stereo with Cascaded Epipolar RAFT","created":"2022-05-09","cited_by_count":51},{"id":"1804.05312","title":"Local Descriptors Optimized for Average Precision","created":"2018-04-15","cited_by_count":43},{"id":"2103.01055","title":"P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching","created":"2021-03-01","cited_by_count":42},{"id":"1912.00623","title":"Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task","created":"2019-12-02","cited_by_count":39},{"id":"2303.07700","title":"PATS: Patch Area Transportation with Subdivision for Local Feature Matching","created":"2023-03-14","cited_by_count":33},{"id":"2303.08384","title":"Rethinking Optical Flow from Geometric Matching Consistent Perspective","created":"2023-03-15","cited_by_count":33},{"id":"2112.03243","title":"Input-level Inductive Biases for 3D Reconstruction","created":"2021-12-06","cited_by_count":31},{"id":"2303.17342","title":"PMatch: Paired Masked Image Modeling for Dense Geometric Matching","created":"2023-03-30","cited_by_count":29},{"id":"2204.10144","title":"A case for using rotation invariant features in state of the art feature matchers","created":"2022-04-21","cited_by_count":27},{"id":"1504.06603","title":"WxBS: Wide Baseline Stereo Generalizations","created":"2015-04-24","cited_by_count":23},{"id":"2008.09497","title":"Single-Image Depth Prediction Makes Feature Matching Easier","created":"2020-08-21","cited_by_count":21},{"id":"2106.07791","title":"DFM: A Performance Baseline for Deep Feature Matching","created":"2021-06-14","cited_by_count":17},{"id":"2403.01569","title":"Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV","created":"2024-03-03","cited_by_count":7},{"id":"2211.15107","title":"A Light Touch Approach to Teaching Transformers Multi-view Geometry","created":"2022-11-28","cited_by_count":6}],"next_cursor":null}