{"list":"other","total":73,"rows":[{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"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":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"1807.10165","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","created":"2018-07-18","cited_by_count":1525},{"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":"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":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"2003.04618","title":"Convolutional Occupancy Networks","created":"2020-03-10","cited_by_count":761},{"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":"2112.00724","title":"RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs","created":"2021-12-01","cited_by_count":615},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"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":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"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":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"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":"2003.01456","title":"Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion","created":"2020-03-03","cited_by_count":343},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"2004.11364","title":"Single-View View Synthesis with Multiplane Images","created":"2020-04-23","cited_by_count":263},{"id":"2004.15021","title":"Consistent Video Depth Estimation","created":"2020-04-30","cited_by_count":220},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"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":"2012.07810","title":"Real-Time High-Resolution Background Matting","created":"2020-12-14","cited_by_count":173},{"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":"1612.02646","title":"Learning Video Object Segmentation from Static Images","created":"2016-12-08","cited_by_count":151},{"id":"1803.08673","title":"Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries","created":"2018-03-23","cited_by_count":145},{"id":"1810.02695","title":"Learning Depth with Convolutional Spatial Propagation Network","created":"2018-10-04","cited_by_count":136},{"id":"2103.14910","title":"MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis","created":"2021-03-27","cited_by_count":133},{"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":"1909.09051","title":"Self-Supervised Monocular Depth Hints","created":"2019-09-19","cited_by_count":127},{"id":"1905.00538","title":"DPSNet: End-to-end Deep Plane Sweep Stereo","created":"2019-05-02","cited_by_count":115},{"id":"2004.00626","title":"Background Matting: The World is Your Green Screen","created":"2020-04-01","cited_by_count":105},{"id":"1911.00767","title":"Learning to Infer Implicit Surfaces without 3D Supervision","created":"2019-11-02","cited_by_count":103},{"id":"2203.15132","title":"LocalBins: Improving Depth Estimation by Learning Local Distributions","created":"2022-03-28","cited_by_count":94},{"id":"1605.02305","title":"Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks","created":"2016-05-08","cited_by_count":91},{"id":"2208.14743","title":"SimpleRecon: 3D Reconstruction Without 3D Convolutions","created":"2022-08-31","cited_by_count":83},{"id":"1807.10264","title":"Layer-structured 3D Scene Inference via View Synthesis","created":"2018-07-26","cited_by_count":82},{"id":"1604.03650","title":"Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks","created":"2016-04-13","cited_by_count":73},{"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":"1708.03088","title":"Semantic Video CNNs through Representation Warping","created":"2017-08-10","cited_by_count":65},{"id":"2104.00622","title":"RGB-D Local Implicit Function for Depth Completion of Transparent Objects","created":"2021-04-01","cited_by_count":64},{"id":"1904.01175","title":"DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality","created":"2019-04-02","cited_by_count":63},{"id":"1807.08563","title":"MVDepthNet: Real-time Multiview Depth Estimation Neural Network","created":"2018-07-23","cited_by_count":59},{"id":"2005.05125","title":"FroDO: From Detections to 3D Objects","created":"2020-05-11","cited_by_count":51},{"id":"2109.01068","title":"SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting","created":"2021-09-02","cited_by_count":48},{"id":"2104.08569","title":"RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features","created":"2021-04-17","cited_by_count":47},{"id":"1904.06397","title":"Multi-View Stereo by Temporal Nonparametric Fusion","created":"2019-04-12","cited_by_count":46},{"id":"2004.00845","title":"Occlusion-Aware Depth Estimation with Adaptive Normal Constraints","created":"2020-04-02","cited_by_count":41},{"id":"2002.12730","title":"Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields","created":"2020-02-28","cited_by_count":40},{"id":"2005.07274","title":"Bi3D: Stereo Depth Estimation via Binary Classifications","created":"2020-05-14","cited_by_count":34},{"id":"1807.08776","title":"Peeking Behind Objects: Layered Depth Prediction from a Single Image","created":"2018-07-23","cited_by_count":23},{"id":"2204.09433","title":"PP-Matting: High-Accuracy Natural Image Matting","created":"2022-04-20","cited_by_count":23},{"id":"2006.05724","title":"Real-time single image depth perception in the wild with handheld devices","created":"2020-06-10","cited_by_count":19},{"id":"2106.08710","title":"Mobile Augmented Reality: User Interfaces, Frameworks, and Intelligence","created":"2021-06-16","cited_by_count":10},{"id":"1912.06268","title":"Inferring Distributions Over Depth from a Single Image","created":"2019-12-12","cited_by_count":8},{"id":"1907.06740","title":"Real-time Hair Segmentation and Recoloring on Mobile GPUs","created":"2019-07-15","cited_by_count":7},{"id":"1912.10637","title":"GrabAR: Occlusion-aware Grabbing Virtual Objects in AR","created":"2019-12-23","cited_by_count":4},{"id":"2010.11800","title":"Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos","created":"2020-10-22","cited_by_count":3}],"next_cursor":null}