{"list":"other","total":57,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"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":"1610.06475","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","created":"2016-10-20","cited_by_count":806},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"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":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1607.02565","title":"Direct Sparse Odometry","created":"2016-07-09","cited_by_count":485},{"id":"1708.03852","title":"VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator","created":"2017-08-13","cited_by_count":423},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"1806.01411","title":"FlowNet3D: Learning Scene Flow in 3D Point Clouds","created":"2018-06-04","cited_by_count":242},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"2006.14822","title":"A survey of loss functions for semantic segmentation","created":"2020-06-26","cited_by_count":217},{"id":"2003.01060","title":"D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry","created":"2020-03-02","cited_by_count":206},{"id":"1711.07837","title":"UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss","created":"2017-11-21","cited_by_count":202},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"1712.03342","title":"Geometry-Aware Learning of Maps for Camera Localization","created":"2017-12-09","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":"1806.05620","title":"DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes","created":"2018-06-14","cited_by_count":134},{"id":"2001.05049","title":"DeepFactors: Real-Time Probabilistic Dense Monocular SLAM","created":"2020-01-14","cited_by_count":117},{"id":"1906.05332","title":"HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds","created":"2019-06-12","cited_by_count":109},{"id":"2011.00359","title":"TartanVO: A Generalizable Learning-based VO","created":"2020-10-31","cited_by_count":108},{"id":"1806.00557","title":"CubeSLAM: Monocular 3D Object SLAM","created":"2018-06-01","cited_by_count":102},{"id":"1804.06120","title":"The TUM VI Benchmark for Evaluating Visual-Inertial Odometry","created":"2018-04-17","cited_by_count":99},{"id":"1809.08379","title":"DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments","created":"2018-09-22","cited_by_count":91},{"id":"1808.01900","title":"DeepTAM: Deep Tracking and Mapping","created":"2018-08-06","cited_by_count":87},{"id":"2012.00212","title":"UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning","created":"2020-12-01","cited_by_count":49},{"id":"2203.15174","title":"Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth","created":"2022-03-29","cited_by_count":48},{"id":"2103.12032","title":"Tangent Space Backpropagation for 3D Transformation Groups","created":"2021-03-22","cited_by_count":40},{"id":"1804.04259","title":"Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation","created":"2018-04-12","cited_by_count":38},{"id":"2003.05102","title":"FlowFusion: Dynamic Dense RGB-D SLAM Based on Optical Flow","created":"2020-03-11","cited_by_count":37},{"id":"1904.11781","title":"EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data Association","created":"2019-04-26","cited_by_count":28},{"id":"1908.06316","title":"Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes","created":"2019-08-17","cited_by_count":27},{"id":"1808.00692","title":"Online Temporal Calibration for Monocular Visual-Inertial Systems","created":"2018-08-02","cited_by_count":26},{"id":"2207.01610","title":"PVO: Panoptic Visual Odometry","created":"2022-07-04","cited_by_count":26},{"id":"1904.06577","title":"Direct Sparse Mapping","created":"2019-04-13","cited_by_count":25},{"id":"2002.08584","title":"Dynamic SLAM: The Need For Speed","created":"2020-02-20","cited_by_count":24},{"id":"2011.08332","title":"EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation","created":"2020-11-16","cited_by_count":22},{"id":"2103.00933","title":"DF-VO: What Should Be Learnt for Visual Odometry?","created":"2021-03-01","cited_by_count":22},{"id":"2104.00099","title":"LIFT-SLAM: a deep-learning feature-based monocular visual SLAM method","created":"2021-03-31","cited_by_count":20},{"id":"2003.12980","title":"ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings","created":"2020-03-29","cited_by_count":17},{"id":"2112.03045","title":"3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video","created":"2021-12-06","cited_by_count":11},{"id":"2008.00072","title":"Dynamic Object Tracking and Masking for Visual SLAM","created":"2020-07-31","cited_by_count":8},{"id":"2003.04569","title":"DymSLAM:4D Dynamic Scene Reconstruction Based on Geometrical Motion Segmentation","created":"2020-03-10","cited_by_count":5},{"id":"1701.05294","title":"Non-Iterative SLAM","created":"2017-01-19","cited_by_count":4},{"id":"2002.03528","title":"Multi-object Monocular SLAM for Dynamic Environments","created":"2020-02-10","cited_by_count":4},{"id":"2009.11219","title":"Dual-SLAM: A framework for robust single camera navigation","created":"2020-09-23","cited_by_count":1}],"next_cursor":null}