{"list":"other","total":101,"rows":[{"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"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":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"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":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"1708.06500","title":"Sparsity Invariant CNNs","created":"2017-08-22","cited_by_count":326},{"id":"2103.06011","title":"DSEC: A Stereo Event Camera Dataset for Driving Scenarios","created":"2021-03-10","cited_by_count":303},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"1801.10202","title":"The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception","created":"2018-01-30","cited_by_count":254},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"2006.14480","title":"One Thousand and One Hours: Self-driving Motion Prediction Dataset","created":"2020-06-25","cited_by_count":240},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","cited_by_count":234},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"2004.15021","title":"Consistent Video Depth Estimation","created":"2020-04-30","cited_by_count":220},{"id":"1701.05498","title":"T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects","created":"2017-01-19","cited_by_count":210},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"2012.05901","title":"Robust Consistent Video Depth Estimation","created":"2020-12-10","cited_by_count":188},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"1612.03153","title":"Panoptic Studio: A Massively Multiview System for Social Interaction Capture","created":"2016-12-09","cited_by_count":173},{"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":"1905.01489","title":"WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving","created":"2019-05-04","cited_by_count":144},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"1405.2941","title":"Cross-view Action Modeling, Learning and Recognition","created":"2014-05-12","cited_by_count":134},{"id":"1909.05483","title":"3D Ken Burns Effect from a Single Image","created":"2019-09-12","cited_by_count":128},{"id":"1910.02550","title":"ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation","created":"2019-10-06","cited_by_count":124},{"id":"1904.11111","title":"Learning the Depths of Moving People by Watching Frozen People","created":"2019-04-25","cited_by_count":120},{"id":"1301.3592","title":"Deep Learning for Detecting Robotic Grasps","created":"2013-01-16","cited_by_count":116},{"id":"2105.14021","title":"Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging","created":"2021-05-28","cited_by_count":104},{"id":"2101.01133","title":"Stereo Correspondence and Reconstruction of Endoscopic Data Challenge","created":"2021-01-04","cited_by_count":103},{"id":"1703.07475","title":"PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding","created":"2017-03-22","cited_by_count":101},{"id":"1807.09620","title":"OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas","created":"2018-07-25","cited_by_count":99},{"id":"1505.05641","title":"Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views","created":"2015-05-21","cited_by_count":94},{"id":"1811.01343","title":"Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset","created":"2018-11-04","cited_by_count":93},{"id":"2102.09320","title":"Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction","created":"2021-02-18","cited_by_count":90},{"id":"1809.00716","title":"InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset","created":"2018-09-03","cited_by_count":87},{"id":"1409.4326","title":"Computing the Stereo Matching Cost with a Convolutional Neural Network","created":"2014-09-15","cited_by_count":74},{"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":"1904.11112","title":"Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes","created":"2019-04-25","cited_by_count":73},{"id":"1602.02481","title":"A Large Dataset of Object Scans","created":"2016-02-08","cited_by_count":64},{"id":"1808.06586","title":"Learning Monocular Depth by Distilling Cross-domain Stereo Networks","created":"2018-08-20","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":"2002.00569","title":"DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data","created":"2020-02-03","cited_by_count":61},{"id":"2003.05691","title":"The Newer College Dataset: Handheld LiDAR, Inertial and Vision with Ground Truth","created":"2020-03-12","cited_by_count":61},{"id":"1708.03292","title":"Learning to Synthesize a 4D RGBD Light Field from a Single Image","created":"2017-08-10","cited_by_count":60},{"id":"2001.06659","title":"Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials","created":"2020-01-18","cited_by_count":56},{"id":"1702.08272","title":"A Dataset for Developing and Benchmarking Active Vision","created":"2017-02-27","cited_by_count":50},{"id":"1904.05822","title":"Learning Single Camera Depth Estimation using Dual-Pixels","created":"2019-04-11","cited_by_count":49},{"id":"1704.02612","title":"BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis","created":"2017-04-09","cited_by_count":46},{"id":"1811.05304","title":"Self-Supervised Learning of Depth and Camera Motion from 360{\\deg} Videos","created":"2018-11-13","cited_by_count":40},{"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":"2010.05537","title":"Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection","created":"2020-10-12","cited_by_count":38},{"id":"2107.12429","title":"MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments","created":"2021-07-26","cited_by_count":38},{"id":"1909.05452","title":"Flow-Motion and Depth Network for Monocular Stereo and Beyond","created":"2019-09-12","cited_by_count":37},{"id":"2109.02749","title":"Pano3D: A Holistic Benchmark and a Solid Baseline for $360^o$ Depth Estimation","created":"2021-09-06","cited_by_count":37},{"id":"2003.11172","title":"Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset","created":"2020-03-25","cited_by_count":36},{"id":"1908.08391","title":"Learning Object-Action Relations from Bimanual Human Demonstration Using Graph Networks","created":"2019-08-22","cited_by_count":29},{"id":"1609.07826","title":"Multiview RGB-D Dataset for Object Instance Detection","created":"2016-09-26","cited_by_count":26},{"id":"1806.09573","title":"Learning Single-Image Depth from Videos using Quality Assessment Networks","created":"2018-06-25","cited_by_count":25},{"id":"2009.01579","title":"DESC: Domain Adaptation for Depth Estimation via Semantic Consistency","created":"2020-09-03","cited_by_count":25},{"id":"1904.10230","title":"A Large RGB-D Dataset for Semi-supervised Monocular Depth Estimation","created":"2019-04-23","cited_by_count":21},{"id":"1910.01275","title":"A Neural Network for Detailed Human Depth Estimation from a Single Image","created":"2019-10-03","cited_by_count":21},{"id":"1604.03692","title":"Learning Social Affordance for Human-Robot Interaction","created":"2016-04-13","cited_by_count":20},{"id":"2102.12010","title":"PixSet : An Opportunity for 3D Computer Vision to Go Beyond Point Clouds With a Full-Waveform LiDAR Dataset","created":"2021-02-24","cited_by_count":20},{"id":"1811.10343","title":"Matchable Image Retrieval by Learning from Surface Reconstruction","created":"2018-11-26","cited_by_count":19},{"id":"1611.10195","title":"POSEidon: Face-from-Depth for Driver Pose Estimation","created":"2016-11-30","cited_by_count":16},{"id":"1904.10681","title":"A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition","created":"2019-04-24","cited_by_count":16},{"id":"1702.08558","title":"DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition","created":"2017-02-27","cited_by_count":15},{"id":"2106.06629","title":"Mirror3D: Depth Refinement for Mirror Surfaces","created":"2021-06-11","cited_by_count":13},{"id":"1604.00999","title":"RGBD Datasets: Past, Present and Future","created":"2016-04-04","cited_by_count":11},{"id":"1709.08480","title":"J-MOD$^{2}$: Joint Monocular Obstacle Detection and Depth Estimation","created":"2017-09-25","cited_by_count":9},{"id":"1910.13708","title":"MonSter: Awakening the Mono in Stereo","created":"2019-10-30","cited_by_count":3},{"id":"2108.02448","title":"MFuseNet: Robust Depth Estimation with Learned Multiscopic Fusion","created":"2021-08-05","cited_by_count":3},{"id":"2108.02671","title":"Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware","created":"2021-08-05","cited_by_count":3}],"next_cursor":"100"}