{"list":"other","total":53,"rows":[{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"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":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1905.00889","title":"Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines","created":"2019-05-02","cited_by_count":672},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"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":"1603.08182","title":"3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions","created":"2016-03-27","cited_by_count":336},{"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":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110},{"id":"1812.04072","title":"PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image","created":"2018-12-10","cited_by_count":105},{"id":"2306.17253","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","created":"2023-06-29","cited_by_count":101},{"id":"1804.06278","title":"PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image","created":"2018-04-17","cited_by_count":77},{"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":"1902.09777","title":"Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding","created":"2019-02-26","cited_by_count":56},{"id":"2208.13241","title":"Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image","created":"2022-08-28","cited_by_count":42},{"id":"2103.14644","title":"Planar Surface Reconstruction from Sparse Views","created":"2021-03-26","cited_by_count":40},{"id":"2103.16694","title":"Geometric Unsupervised Domain Adaptation for Semantic Segmentation","created":"2021-03-30","cited_by_count":33},{"id":"2107.13108","title":"PlaneTR: Structure-Guided Transformers for 3D Plane Recovery","created":"2021-07-27","cited_by_count":33},{"id":"2312.14198","title":"ZeroShape: Regression-based Zero-shot Shape Reconstruction","created":"2023-12-21","cited_by_count":30},{"id":"2203.12082","title":"PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo","created":"2022-03-22","cited_by_count":29},{"id":"2206.07710","title":"PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos","created":"2022-06-15","cited_by_count":27},{"id":"2208.04307","title":"PlaneFormers: From Sparse View Planes to 3D Reconstruction","created":"2022-08-08","cited_by_count":26},{"id":"2211.16799","title":"NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction","created":"2022-11-30","cited_by_count":21},{"id":"2305.16411","title":"ZeroAvatar: Zero-shot 3D Avatar Generation from a Single Image","created":"2023-05-25","cited_by_count":18},{"id":"2311.05770","title":"PolyMaX: General Dense Prediction with Mask Transformer","created":"2023-11-09","cited_by_count":14},{"id":"2406.08960","title":"AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings","created":"2024-06-13","cited_by_count":13},{"id":"2303.05937","title":"Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction","created":"2023-03-10","cited_by_count":12}],"next_cursor":null}