{"list":"other","total":62,"rows":[{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"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":"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":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"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":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1603.04467","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","created":"2016-03-14","cited_by_count":664},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"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":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"1904.06587","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","created":"2019-04-13","cited_by_count":244},{"id":"2104.00681","title":"NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video","created":"2021-04-01","cited_by_count":241},{"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":"2003.01060","title":"D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry","created":"2020-03-02","cited_by_count":206},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2104.14540","title":"The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth","created":"2021-04-29","cited_by_count":190},{"id":"2012.05901","title":"Robust Consistent Video Depth Estimation","created":"2020-12-10","cited_by_count":188},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"2005.06209","title":"On the uncertainty of self-supervised monocular depth estimation","created":"2020-05-13","cited_by_count":182},{"id":"1709.08429","title":"DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks","created":"2017-09-25","cited_by_count":175},{"id":"1806.04807","title":"BA-Net: Dense Bundle Adjustment Network","created":"2018-06-13","cited_by_count":175},{"id":"1502.07411","title":"Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields","created":"2015-02-26","cited_by_count":169},{"id":"2004.01294","title":"Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera","created":"2020-04-02","cited_by_count":166},{"id":"2007.06936","title":"Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance","created":"2020-07-14","cited_by_count":148},{"id":"1509.05909","title":"Modelling Uncertainty in Deep Learning for Camera Relocalization","created":"2015-09-19","cited_by_count":134},{"id":"1907.05820","title":"Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera","created":"2019-07-12","cited_by_count":130},{"id":"2003.13951","title":"Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume","created":"2020-03-31","cited_by_count":116},{"id":"1702.02706","title":"Semi-Supervised Deep Learning for Monocular Depth Map Prediction","created":"2017-02-09","cited_by_count":109},{"id":"2107.02191","title":"TransformerFusion: Monocular RGB Scene Reconstruction using Transformers","created":"2021-07-05","cited_by_count":106},{"id":"1704.07804","title":"SfM-Net: Learning of Structure and Motion from Video","created":"2017-04-25","cited_by_count":89},{"id":"1808.01900","title":"DeepTAM: Deep Tracking and Mapping","created":"2018-08-06","cited_by_count":87},{"id":"2010.16404","title":"Unsupervised Monocular Depth Learning in Dynamic Scenes","created":"2020-10-30","cited_by_count":84},{"id":"1905.07005","title":"How do neural networks see depth in single images?","created":"2019-05-16","cited_by_count":82},{"id":"1901.02571","title":"Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera","created":"2019-01-09","cited_by_count":69},{"id":"2012.02177","title":"DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion","created":"2020-12-03","cited_by_count":68},{"id":"2011.11814","title":"MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera","created":"2020-11-24","cited_by_count":59},{"id":"2108.01166","title":"Consistent Depth of Moving Objects in Video","created":"2021-08-02","cited_by_count":56},{"id":"1909.03751","title":"Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching","created":"2019-09-09","cited_by_count":55},{"id":"1701.08376","title":"VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem","created":"2017-01-29","cited_by_count":51},{"id":"1906.05717","title":"Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics","created":"2019-06-12","cited_by_count":49},{"id":"1801.06397","title":"What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?","created":"2018-01-19","cited_by_count":44},{"id":"2103.16694","title":"Geometric Unsupervised Domain Adaptation for Semantic Segmentation","created":"2021-03-30","cited_by_count":33},{"id":"1809.02966","title":"LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo","created":"2018-09-09","cited_by_count":28},{"id":"1708.04398","title":"Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames","created":"2017-08-15","cited_by_count":27},{"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":"1806.10556","title":"Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding","created":"2018-06-27","cited_by_count":24},{"id":"1911.09092","title":"Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene","created":"2019-11-19","cited_by_count":22},{"id":"1912.06268","title":"Inferring Distributions Over Depth from a Single Image","created":"2019-12-12","cited_by_count":8},{"id":"1912.09351","title":"Instance-wise Depth and Motion Learning from Monocular Videos","created":"2019-12-19","cited_by_count":7}],"next_cursor":null}