{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"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":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"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":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"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":"1804.01654","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","created":"2018-04-05","cited_by_count":651},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1610.07584","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","created":"2016-10-24","cited_by_count":558},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"1907.03739","title":"Point-Voxel CNN for Efficient 3D Deep Learning","created":"2019-07-08","cited_by_count":343},{"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":"1807.10267","title":"Generating 3D faces using Convolutional Mesh Autoencoders","created":"2018-07-26","cited_by_count":268},{"id":"1905.03678","title":"What Do Single-view 3D Reconstruction Networks Learn?","created":"2019-05-09","cited_by_count":260},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"1907.12209","title":"Enforcing geometric constraints of virtual normal for depth prediction","created":"2019-07-29","cited_by_count":234},{"id":"2004.04727","title":"3D Photography using Context-aware Layered Depth Inpainting","created":"2020-04-09","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":"2007.10042","title":"Non-Local Spatial Propagation Network for Depth Completion","created":"2020-07-20","cited_by_count":195},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"1502.07411","title":"Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields","created":"2015-02-26","cited_by_count":169},{"id":"1709.07492","title":"Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image","created":"2017-09-21","cited_by_count":161},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"1810.02695","title":"Learning Depth with Convolutional Spatial Propagation Network","created":"2018-10-04","cited_by_count":136},{"id":"1812.00488","title":"DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image","created":"2018-12-02","cited_by_count":129},{"id":"1909.05483","title":"3D Ken Burns Effect from a Single Image","created":"2019-09-12","cited_by_count":128},{"id":"1904.11111","title":"Learning the Depths of Moving People by Watching Frozen People","created":"2019-04-25","cited_by_count":120},{"id":"1803.09326","title":"Deep Depth Completion of a Single RGB-D Image","created":"2018-03-25","cited_by_count":110},{"id":"1808.00150","title":"Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network","created":"2018-08-01","cited_by_count":110},{"id":"1911.05377","title":"CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion","created":"2019-11-13","cited_by_count":110},{"id":"1910.06727","title":"Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints","created":"2019-10-15","cited_by_count":108},{"id":"2011.06961","title":"Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis","created":"2020-11-13","cited_by_count":84},{"id":"1710.01020","title":"Learning Affinity via Spatial Propagation Networks","created":"2017-10-03","cited_by_count":79},{"id":"1904.02028","title":"CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth","created":"2019-04-03","cited_by_count":75},{"id":"1904.11112","title":"Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes","created":"2019-04-25","cited_by_count":73},{"id":"1809.05068","title":"Learning Shape Priors for Single-View 3D Completion and Reconstruction","created":"2018-09-13","cited_by_count":68},{"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":"2002.00569","title":"DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data","created":"2020-02-03","cited_by_count":61},{"id":"2103.04216","title":"Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction","created":"2021-03-07","cited_by_count":48},{"id":"1712.01259","title":"A Perceptual Measure for Deep Single Image Camera Calibration","created":"2017-12-02","cited_by_count":45},{"id":"1903.05421","title":"Depth Coefficients for Depth Completion","created":"2019-03-13","cited_by_count":41},{"id":"2003.11172","title":"Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset","created":"2020-03-25","cited_by_count":36},{"id":"1908.08344","title":"Indoor Depth Completion with Boundary Consistency and Self-Attention","created":"2019-08-22","cited_by_count":29},{"id":"1806.09573","title":"Learning Single-Image Depth from Videos using Quality Assessment Networks","created":"2018-06-25","cited_by_count":25},{"id":"2104.07350","title":"Depth Completion using Plane-Residual Representation","created":"2021-04-15","cited_by_count":24},{"id":"1909.07701","title":"Task-Aware Monocular Depth Estimation for 3D Object Detection","created":"2019-09-17","cited_by_count":22},{"id":"2204.01268","title":"Improving Monocular Visual Odometry Using Learned Depth","created":"2022-04-04","cited_by_count":17},{"id":"2202.01470","title":"Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth","created":"2022-02-03","cited_by_count":11}],"next_cursor":null}