{"list":"other","total":89,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"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":"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":"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":"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":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"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":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"1607.02565","title":"Direct Sparse Odometry","created":"2016-07-09","cited_by_count":485},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"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":"1907.10326","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","created":"2019-07-24","cited_by_count":382},{"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":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"1708.06500","title":"Sparsity Invariant CNNs","created":"2017-08-22","cited_by_count":326},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"2104.02409","title":"Learning to Estimate Hidden Motions with Global Motion Aggregation","created":"2021-04-06","cited_by_count":224},{"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":"2004.15021","title":"Consistent Video Depth Estimation","created":"2020-04-30","cited_by_count":220},{"id":"1903.02351","title":"CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning","created":"2019-03-06","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":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2103.09213","title":"Back to the Feature: Learning Robust Camera Localization from Pixels to Pose","created":"2021-03-16","cited_by_count":199},{"id":"2109.01129","title":"NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo","created":"2021-09-02","cited_by_count":192},{"id":"2104.14540","title":"The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth","created":"2021-04-29","cited_by_count":190},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"1802.05522","title":"Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints","created":"2018-02-15","cited_by_count":179},{"id":"1904.04998","title":"Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras","created":"2019-04-10","cited_by_count":170},{"id":"1803.03893","title":"Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction","created":"2018-03-11","cited_by_count":159},{"id":"1811.06152","title":"Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos","created":"2018-11-15","cited_by_count":155},{"id":"1712.00175","title":"Learning Depth from Monocular Videos using Direct Methods","created":"2017-12-01","cited_by_count":154},{"id":"1809.01649","title":"DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency","created":"2018-09-05","cited_by_count":148},{"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":"2007.10603","title":"Feature-metric Loss for Self-supervised Learning of Depth and Egomotion","created":"2020-07-21","cited_by_count":140},{"id":"2002.12319","title":"Semantically-Guided Representation Learning for Self-Supervised Monocular Depth","created":"2020-02-27","cited_by_count":134},{"id":"1904.05290","title":"Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation","created":"2019-04-10","cited_by_count":131},{"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":"1905.00538","title":"DPSNet: End-to-end Deep Plane Sweep Stereo","created":"2019-05-02","cited_by_count":115},{"id":"1810.06125","title":"Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding","created":"2018-10-14","cited_by_count":101},{"id":"1903.03273","title":"FastDepth: Fast Monocular Depth Estimation on Embedded Systems","created":"2019-03-08","cited_by_count":94},{"id":"2010.16404","title":"Unsupervised Monocular Depth Learning in Dynamic Scenes","created":"2020-10-30","cited_by_count":84},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77},{"id":"2001.02613","title":"Don't Forget The Past: Recurrent Depth Estimation from Monocular Video","created":"2020-01-08","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":"1901.02571","title":"Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera","created":"2019-01-09","cited_by_count":69},{"id":"2105.11610","title":"Unsupervised Scale-consistent Depth Learning from Video","created":"2021-05-25","cited_by_count":69},{"id":"1603.08695","title":"Learning to Refine Object Segments","created":"2016-03-29","cited_by_count":67},{"id":"2110.09482","title":"Self-Supervised Monocular Depth Estimation with Internal Feature Fusion","created":"2021-10-18","cited_by_count":67},{"id":"2204.07616","title":"Multi-Frame Self-Supervised Depth with Transformers","created":"2022-04-15","cited_by_count":64},{"id":"2204.08442","title":"Deep Equilibrium Optical Flow Estimation","created":"2022-04-18","cited_by_count":64},{"id":"2007.13215","title":"OASIS: A Large-Scale Dataset for Single Image 3D in the Wild","created":"2020-07-26","cited_by_count":62},{"id":"1904.01870","title":"Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation","created":"2019-04-03","cited_by_count":61},{"id":"1807.08563","title":"MVDepthNet: Real-time Multiview Depth Estimation Neural Network","created":"2018-07-23","cited_by_count":59},{"id":"1803.01599","title":"AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation","created":"2018-03-05","cited_by_count":54},{"id":"2008.03633","title":"Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes","created":"2020-08-09","cited_by_count":50},{"id":"1906.05717","title":"Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics","created":"2019-06-12","cited_by_count":49},{"id":"2108.05773","title":"Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation","created":"2021-08-12","cited_by_count":47},{"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":"2004.00845","title":"Occlusion-Aware Depth Estimation with Adaptive Normal Constraints","created":"2020-04-02","cited_by_count":41},{"id":"2003.14030","title":"Distilled Semantics for Comprehensive Scene Understanding from Videos","created":"2020-03-31","cited_by_count":39},{"id":"2007.10983","title":"Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling","created":"2020-07-21","cited_by_count":39},{"id":"1604.07480","title":"Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks","created":"2016-04-25","cited_by_count":36},{"id":"1807.03959","title":"Deep attention-based classification network for robust depth prediction","created":"2018-07-11","cited_by_count":36},{"id":"2103.16694","title":"Geometric Unsupervised Domain Adaptation for Semantic Segmentation","created":"2021-03-30","cited_by_count":33},{"id":"1904.11932","title":"GN-Net: The Gauss-Newton Loss for Multi-Weather Relocalization","created":"2019-04-26","cited_by_count":32},{"id":"2010.06323","title":"LM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalization","created":"2020-10-13","cited_by_count":28},{"id":"2006.04026","title":"SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation","created":"2020-06-07","cited_by_count":25},{"id":"2008.06630","title":"Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion","created":"2020-08-15","cited_by_count":20},{"id":"2006.09876","title":"Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues","created":"2020-06-17","cited_by_count":19},{"id":"1902.09103","title":"Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation","created":"2019-02-25","cited_by_count":17},{"id":"2106.11641","title":"Confidence-Aware Learning for Camouflaged Object Detection","created":"2021-06-22","cited_by_count":5},{"id":"1804.11332","title":"On the iterative refinement of densely connected representation levels for semantic segmentation","created":"2018-04-30","cited_by_count":3},{"id":"2009.00842","title":"Retaining Image Feature Matching Performance Under Low Light Conditions","created":"2020-09-02","cited_by_count":3}],"next_cursor":null}