{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"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":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"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":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"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":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"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":"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":"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":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1912.02413","title":"BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition","created":"2019-12-05","cited_by_count":403},{"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":"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":"2004.15021","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":"2004.04727","title":"3D Photography using Context-aware Layered Depth Inpainting","created":"2020-04-09","cited_by_count":206},{"id":"2204.00987","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","created":"2022-04-03","cited_by_count":168},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"1812.11941","title":"High Quality Monocular Depth Estimation via Transfer Learning","created":"2018-12-31","cited_by_count":133},{"id":"2203.14211","title":"DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation","created":"2022-03-27","cited_by_count":118},{"id":"2205.13543","title":"Revealing the Dark Secrets of Masked Image Modeling","created":"2022-05-26","cited_by_count":117},{"id":"2204.02091","title":"P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior","created":"2022-04-05","cited_by_count":107},{"id":"1411.6387","title":"Deep Convolutional Neural Fields for Depth Estimation from a Single Image","created":"2014-11-24","cited_by_count":106},{"id":"2203.15132","title":"LocalBins: Improving Depth Estimation by Learning Local Distributions","created":"2022-03-28","cited_by_count":94},{"id":"2210.09071","title":"Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention","created":"2022-10-17","cited_by_count":93},{"id":"2004.01314","title":"Towards Better Generalization: Joint Depth-Pose Learning without PoseNet","created":"2020-04-03","cited_by_count":85},{"id":"2105.11610","title":"Unsupervised Scale-consistent Depth Learning from Video","created":"2021-05-25","cited_by_count":69},{"id":"2201.07436","title":"Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth","created":"2022-01-19","cited_by_count":58},{"id":"2111.08600","title":"Towards Real-Time Monocular Depth Estimation for Robotics: A Survey","created":"2021-11-16","cited_by_count":57},{"id":"2302.06556","title":"VA-DepthNet: A Variational Approach to Single Image Depth Prediction","created":"2023-02-13","cited_by_count":54},{"id":"2301.02229","title":"All in Tokens: Unifying Output Space of Visual Tasks via Soft Token","created":"2023-01-05","cited_by_count":52},{"id":"2112.02306","title":"Toward Practical Monocular Indoor Depth Estimation","created":"2021-12-04","cited_by_count":42},{"id":"2007.07696","title":"P$^{2}$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation","created":"2020-07-15","cited_by_count":41},{"id":"2006.02708","title":"Auto-Rectify Network for Unsupervised Indoor Depth Estimation","created":"2020-06-04","cited_by_count":39},{"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":"2108.08574","title":"StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation","created":"2021-08-19","cited_by_count":36},{"id":"2106.02022","title":"Single Image Depth Prediction with Wavelet Decomposition","created":"2021-06-03","cited_by_count":34},{"id":"1910.08898","title":"Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments","created":"2019-10-20","cited_by_count":31},{"id":"2210.03676","title":"IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty","created":"2022-10-07","cited_by_count":30},{"id":"1904.02251","title":"StereoDRNet: Dilated Residual Stereo Net","created":"2019-04-03","cited_by_count":29},{"id":"2110.09772","title":"Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry","created":"2021-10-19","cited_by_count":27},{"id":"2206.08802","title":"Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets","created":"2022-06-17","cited_by_count":25},{"id":"1906.08967","title":"Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion","created":"2019-06-21","cited_by_count":20},{"id":"1803.00891","title":"Monocular Depth Estimation using Multi-Scale Continuous CRFs as Sequential Deep Networks","created":"2018-03-01","cited_by_count":19},{"id":"2208.10762","title":"Depth Map Decomposition for Monocular Depth Estimation","created":"2022-08-23","cited_by_count":16},{"id":"2110.05839","title":"PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation","created":"2021-10-12","cited_by_count":12},{"id":"2203.09824","title":"Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?","created":"2022-03-18","cited_by_count":8},{"id":"2003.06945","title":"Scene Completeness-Aware Lidar Depth Completion for Driving Scenario","created":"2020-03-15","cited_by_count":7},{"id":"1906.02429","title":"Occluded Face Recognition Using Low-rank Regression with Generalized Gradient Direction","created":"2019-06-06","cited_by_count":6},{"id":"2306.02878","title":"Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data","created":"2023-06-05","cited_by_count":6},{"id":"2006.07802","title":"Geometry-Aware Instance Segmentation with Disparity Maps","created":"2020-06-14","cited_by_count":4},{"id":"1906.02426","title":"Salient Building Outline Enhancement and Extraction Using Iterative L0 Smoothing and Line Enhancing","created":"2019-06-06","cited_by_count":3},{"id":"2305.07269","title":"Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction","created":"2023-05-12","cited_by_count":3},{"id":"1806.03051","title":"Deep multi-scale architectures for monocular depth estimation","created":"2018-06-08","cited_by_count":2},{"id":"1906.02433","title":"Nonconvex Approach for Sparse and Low-Rank Constrained Models with Dual Momentum","created":"2019-06-06","cited_by_count":2}],"next_cursor":null}