{"list":"other","total":75,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"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":"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":"2010.07492","title":"NeRF++: Analyzing and Improving Neural Radiance Fields","created":"2020-10-15","cited_by_count":861},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2107.02791","title":"Depth-supervised NeRF: Fewer Views and Faster Training for Free","created":"2021-07-06","cited_by_count":735},{"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":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"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":"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":"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":"1907.12209","title":"Enforcing geometric constraints of virtual normal for depth prediction","created":"2019-07-29","cited_by_count":234},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","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":"2108.13826","title":"Self-Calibrating Neural Radiance Fields","created":"2021-08-31","cited_by_count":204},{"id":"1708.05375","title":"Learning a Multi-View Stereo Machine","created":"2017-08-17","cited_by_count":194},{"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":"2011.02910","title":"Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers","created":"2020-11-05","cited_by_count":190},{"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":"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":"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":"2102.07064","title":"NeRF--: Neural Radiance Fields Without Known Camera Parameters","created":"2021-02-14","cited_by_count":155},{"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":"2006.04902","title":"What Matters in Unsupervised Optical Flow","created":"2020-06-08","cited_by_count":124},{"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":"1702.02706","title":"Semi-Supervised Deep Learning for Monocular Depth Map Prediction","created":"2017-02-09","cited_by_count":109},{"id":"1905.07005","title":"How do neural networks see depth in single images?","created":"2019-05-16","cited_by_count":82},{"id":"2004.02760","title":"Guiding Monocular Depth Estimation Using Depth-Attention Volume","created":"2020-04-06","cited_by_count":82},{"id":"2001.02613","title":"Don't Forget The Past: Recurrent Depth Estimation from Monocular Video","created":"2020-01-08","cited_by_count":71},{"id":"2004.04143","title":"Self-Supervised Monocular Scene Flow Estimation","created":"2020-04-08","cited_by_count":64},{"id":"1904.01870","title":"Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation","created":"2019-04-03","cited_by_count":61},{"id":"1908.03706","title":"Exploiting temporal consistency for real-time video depth estimation","created":"2019-08-10","cited_by_count":61},{"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":"2008.07130","title":"Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation","created":"2020-08-17","cited_by_count":34},{"id":"2103.16694","title":"Geometric Unsupervised Domain Adaptation for Semantic Segmentation","created":"2021-03-30","cited_by_count":33},{"id":"2105.02216","title":"Self-Supervised Multi-Frame Monocular Scene Flow","created":"2021-05-05","cited_by_count":29},{"id":"1910.01765","title":"Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances","created":"2019-10-04","cited_by_count":27},{"id":"2110.08192","title":"Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation","created":"2021-10-15","cited_by_count":27},{"id":"2006.04026","title":"SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation","created":"2020-06-07","cited_by_count":25},{"id":"2103.12209","title":"Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision","created":"2021-03-22","cited_by_count":24},{"id":"2009.03787","title":"Self-Supervised Scale Recovery for Monocular Depth and Egomotion Estimation","created":"2020-09-08","cited_by_count":21},{"id":"1806.01677","title":"Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching","created":"2018-06-05","cited_by_count":20},{"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":"1912.10615","title":"Neural Outlier Rejection for Self-Supervised Keypoint Learning","created":"2019-12-23","cited_by_count":16},{"id":"1912.03426","title":"Self-Supervised 3D Keypoint Learning for Ego-motion Estimation","created":"2019-12-07","cited_by_count":12},{"id":"2011.09594","title":"Deep Multi-view Depth Estimation with Predicted Uncertainty","created":"2020-11-19","cited_by_count":11},{"id":"2004.13077","title":"Self-Supervised Attention Learning for Depth and Ego-motion Estimation","created":"2020-04-27","cited_by_count":2}],"next_cursor":null}