{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"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":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"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":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"id":"1611.05705","title":"DSAC - Differentiable RANSAC for Camera Localization","created":"2016-11-17","cited_by_count":266},{"id":"1910.02190","title":"Kornia: an Open Source Differentiable Computer Vision Library for PyTorch","created":"2019-10-05","cited_by_count":232},{"id":"2208.04726","title":"Deep Patch Visual Odometry","created":"2022-08-08","cited_by_count":190},{"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":"1912.05909","title":"MAGSAC++, a fast, reliable and accurate robust estimator","created":"2019-12-11","cited_by_count":161},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147},{"id":"1803.07469","title":"MAGSAC: marginalizing sample consensus","created":"2018-03-20","cited_by_count":123},{"id":"2001.05049","title":"DeepFactors: Real-Time Probabilistic Dense Monocular SLAM","created":"2020-01-14","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":"2011.00359","title":"TartanVO: A Generalizable Learning-based VO","created":"2020-10-31","cited_by_count":108},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102},{"id":"1809.08379","title":"DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments","created":"2018-09-22","cited_by_count":91},{"id":"1807.08865","title":"StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction","created":"2018-07-24","cited_by_count":88},{"id":"1809.00716","title":"InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset","created":"2018-09-03","cited_by_count":87},{"id":"2305.04926","title":"RelPose++: Recovering 6D Poses from Sparse-view Observations","created":"2023-05-08","cited_by_count":87},{"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":"2106.03336","title":"Wide-Baseline Relative Camera Pose Estimation with Directional Learning","created":"2021-06-07","cited_by_count":49},{"id":"2101.00591","title":"Progressive Correspondence Pruning by Consensus Learning","created":"2021-01-03","cited_by_count":46},{"id":"1903.01292","title":"The StreetLearn Environment and Dataset","created":"2019-03-04","cited_by_count":42},{"id":"2104.13530","title":"Extreme Rotation Estimation using Dense Correlation Volumes","created":"2021-04-28","cited_by_count":42},{"id":"2103.14644","title":"Planar Surface Reconstruction from Sparse Views","created":"2021-03-26","cited_by_count":40},{"id":"2208.08988","title":"The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs","created":"2022-08-18","cited_by_count":38},{"id":"2110.02951","title":"Video Autoencoder: self-supervised disentanglement of static 3D structure and motion","created":"2021-10-06","cited_by_count":34},{"id":"2303.07700","title":"PATS: Patch Area Transportation with Subdivision for Local Feature Matching","created":"2023-03-14","cited_by_count":33},{"id":"2309.02420","title":"Doppelgangers: Learning to Disambiguate Images of Similar Structures","created":"2023-09-05","cited_by_count":32},{"id":"1809.08402","title":"RPNet: an End-to-End Network for Relative Camera Pose Estimation","created":"2018-09-22","cited_by_count":31},{"id":"2207.08427","title":"Adaptive Assignment for Geometry Aware Local Feature Matching","created":"2022-07-18","cited_by_count":30},{"id":"2212.13185","title":"Generalized Differentiable RANSAC","created":"2022-12-26","cited_by_count":30},{"id":"2208.04307","title":"PlaneFormers: From Sparse View Planes to 3D Reconstruction","created":"2022-08-08","cited_by_count":26},{"id":"1803.04360","title":"Beyond Gr\\\"obner Bases: Basis Selection for Minimal Solvers","created":"2018-03-12","cited_by_count":25},{"id":"1504.06603","title":"WxBS: Wide Baseline Stereo Generalizations","created":"2015-04-24","cited_by_count":23},{"id":"1901.00063","title":"Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion","created":"2018-12-31","cited_by_count":22},{"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":"1912.11695","title":"Extreme Relative Pose Network under Hybrid Representations","created":"2019-12-25","cited_by_count":19},{"id":"2205.01694","title":"End2End Multi-View Feature Matching with Differentiable Pose Optimization","created":"2022-05-03","cited_by_count":19},{"id":"2007.13727","title":"Associative3D: Volumetric Reconstruction from Sparse Views","created":"2020-07-27","cited_by_count":18},{"id":"2309.16772","title":"XVO: Generalized Visual Odometry via Cross-Modal Self-Training","created":"2023-09-28","cited_by_count":18},{"id":"2306.01596","title":"Two-View Geometry Scoring Without Correspondences","created":"2023-06-02","cited_by_count":11},{"id":"2401.10886","title":"SCENES: Subpixel Correspondence Estimation With Epipolar Supervision","created":"2024-01-19","cited_by_count":1}],"next_cursor":null}