{"list":"other","total":80,"rows":[{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"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":"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":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"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":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1712.04621","title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","created":"2017-12-13","cited_by_count":370},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"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":"1901.02985","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","created":"2019-01-10","cited_by_count":260},{"id":"1907.12209","title":"Enforcing geometric constraints of virtual normal for depth prediction","created":"2019-07-29","cited_by_count":234},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"2012.01411","title":"PatchmatchNet: Learned Multi-View Patchmatch Stereo","created":"2020-12-02","cited_by_count":207},{"id":"2003.01060","title":"D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry","created":"2020-03-02","cited_by_count":206},{"id":"2004.09548","title":"AANet: Adaptive Aggregation Network for Efficient Stereo Matching","created":"2020-04-20","cited_by_count":202},{"id":"2007.10042","title":"Non-Local Spatial Propagation Network for Depth Completion","created":"2020-07-20","cited_by_count":195},{"id":"2005.06209","title":"On the uncertainty of self-supervised monocular depth estimation","created":"2020-05-13","cited_by_count":182},{"id":"1802.05522","title":"Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints","created":"2018-02-15","cited_by_count":179},{"id":"1502.07411","title":"Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields","created":"2015-02-26","cited_by_count":169},{"id":"1803.03893","title":"Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction","created":"2018-03-11","cited_by_count":159},{"id":"1712.00175","title":"Learning Depth from Monocular Videos using Direct Methods","created":"2017-12-01","cited_by_count":154},{"id":"1809.01649","title":"DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency","created":"2018-09-05","cited_by_count":148},{"id":"2007.06936","title":"Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance","created":"2020-07-14","cited_by_count":148},{"id":"2103.00783","title":"PENet: Towards Precise and Efficient Image Guided Depth Completion","created":"2021-03-01","cited_by_count":146},{"id":"1807.00275","title":"Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera","created":"2018-07-01","cited_by_count":140},{"id":"2208.03543","title":"MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer","created":"2022-08-06","cited_by_count":136},{"id":"2002.12319","title":"Semantically-Guided Representation Learning for Self-Supervised Monocular Depth","created":"2020-02-27","cited_by_count":134},{"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":"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":"1909.09051","title":"Self-Supervised Monocular Depth Hints","created":"2019-09-19","cited_by_count":127},{"id":"2012.07356","title":"HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation","created":"2020-12-14","cited_by_count":115},{"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":"2211.13202","title":"Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation","created":"2022-11-23","cited_by_count":100},{"id":"2304.13030","title":"CompletionFormer: Depth Completion with Convolutions and Vision Transformers","created":"2023-04-25","cited_by_count":93},{"id":"1905.08616","title":"Unsupervised Depth Completion from Visual Inertial Odometry","created":"2019-05-15","cited_by_count":89},{"id":"1902.05356","title":"Sparse and noisy LiDAR completion with RGB guidance and uncertainty","created":"2019-02-14","cited_by_count":79},{"id":"1808.00769","title":"Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation","created":"2018-08-02","cited_by_count":76},{"id":"2202.09769","title":"Dynamic Spatial Propagation Network for Depth Completion","created":"2022-02-20","cited_by_count":71},{"id":"1704.02157","title":"Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation","created":"2017-04-07","cited_by_count":70},{"id":"1904.04144","title":"Learning monocular depth estimation infusing traditional stereo knowledge","created":"2019-04-08","cited_by_count":64},{"id":"2108.10531","title":"Unsupervised Depth Completion with Calibrated Backprojection Layers","created":"2021-08-24","cited_by_count":61},{"id":"1901.10034","title":"Dense Depth Posterior (DDP) from Single Image and Sparse Range","created":"2019-01-28","cited_by_count":57},{"id":"2006.03349","title":"Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End","created":"2020-06-05","cited_by_count":55},{"id":"2008.04017","title":"SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Driving","created":"2020-08-10","cited_by_count":48},{"id":"1803.05648","title":"LEGO: Learning Edge with Geometry all at Once by Watching Videos","created":"2018-03-15","cited_by_count":47},{"id":"1903.07309","title":"Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction","created":"2019-03-18","cited_by_count":44},{"id":"2006.08602","title":"Targeted Adversarial Perturbations for Monocular Depth Prediction","created":"2020-06-12","cited_by_count":40},{"id":"1902.00761","title":"DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completion","created":"2019-02-02","cited_by_count":38},{"id":"2106.02994","title":"Learning Topology from Synthetic Data for Unsupervised Depth Completion","created":"2021-06-06","cited_by_count":38},{"id":"1808.01606","title":"Learning monocular depth estimation with unsupervised trinocular assumptions","created":"2018-08-05","cited_by_count":36},{"id":"1807.11130","title":"Geo-Supervised Visual Depth Prediction","created":"2018-07-30","cited_by_count":33},{"id":"2106.03010","title":"An Adaptive Framework for Learning Unsupervised Depth Completion","created":"2021-06-06","cited_by_count":30},{"id":"2008.01034","title":"Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data","created":"2020-08-03","cited_by_count":28},{"id":"2211.10994","title":"DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion","created":"2022-11-20","cited_by_count":27},{"id":"2009.12840","title":"Adaptive confidence thresholding for monocular depth estimation","created":"2020-09-27","cited_by_count":25},{"id":"1806.10556","title":"Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding","created":"2018-06-27","cited_by_count":24},{"id":"2203.16034","title":"Monitored Distillation for Positive Congruent Depth Completion","created":"2022-03-30","cited_by_count":24},{"id":"1912.10336","title":"Depth Completion via Deep Basis Fitting","created":"2019-12-21","cited_by_count":23},{"id":"2103.15254","title":"Bayesian Deep Basis Fitting for Depth Completion with Uncertainty","created":"2021-03-29","cited_by_count":23},{"id":"2009.10142","title":"Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations","created":"2020-09-21","cited_by_count":19},{"id":"2112.06116","title":"Stereoscopic Universal Perturbations across Different Architectures and Datasets","created":"2021-12-12","cited_by_count":17},{"id":"2204.13877","title":"Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM","created":"2022-04-29","cited_by_count":10},{"id":"2310.03967","title":"Sub-token ViT Embedding via Stochastic Resonance Transformers","created":"2023-10-06","cited_by_count":9},{"id":"1908.11092","title":"Minimum Delay Object Detection From Video","created":"2019-08-29","cited_by_count":8},{"id":"2109.08791","title":"Small Lesion Segmentation in Brain MRIs with Subpixel Embedding","created":"2021-09-18","cited_by_count":5}],"next_cursor":null}