{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1812.02822","title":"Learning Implicit Fields for Generative Shape Modeling","created":"2018-12-06","cited_by_count":1060},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"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":"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":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"1912.06378","title":"Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching","created":"2019-12-13","cited_by_count":417},{"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":"1403.6382","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","created":"2014-03-23","cited_by_count":316},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"1905.03678","title":"What Do Single-view 3D Reconstruction Networks Learn?","created":"2019-05-09","cited_by_count":260},{"id":"1904.06587","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","created":"2019-04-13","cited_by_count":244},{"id":"2104.00681","title":"NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video","created":"2021-04-01","cited_by_count":241},{"id":"1903.04025","title":"Group-wise Correlation Stereo Network","created":"2019-03-10","cited_by_count":235},{"id":"2004.11540","title":"Deep Global Registration","created":"2020-04-24","cited_by_count":229},{"id":"2003.10432","title":"Atlas: End-to-End 3D Scene Reconstruction from Posed Images","created":"2020-03-23","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":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2011.02910","title":"Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers","created":"2020-11-05","cited_by_count":190},{"id":"2103.14167","title":"COTR: Correspondence Transformer for Matching Across Images","created":"2021-03-25","cited_by_count":183},{"id":"1711.05971","title":"Learning to Find Good Correspondences","created":"2017-11-16","cited_by_count":176},{"id":"1810.10510","title":"Neighbourhood Consensus Networks","created":"2018-10-24","cited_by_count":174},{"id":"2007.11498","title":"CrossTransformers: spatially-aware few-shot transfer","created":"2020-07-22","cited_by_count":174},{"id":"2010.13501","title":"Hierarchical Neural Architecture Search for Deep Stereo Matching","created":"2020-10-26","cited_by_count":166},{"id":"1912.08329","title":"Cost Volume Pyramid Based Depth Inference for Multi-View Stereo","created":"2019-12-18","cited_by_count":154},{"id":"1606.03798","title":"Deep Image Homography Estimation","created":"2016-06-13","cited_by_count":136},{"id":"1708.01749","title":"SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis","created":"2017-08-05","cited_by_count":128},{"id":"1912.06704","title":"Hierarchical Deep Stereo Matching on High-resolution Images","created":"2019-12-13","cited_by_count":126},{"id":"2005.04551","title":"Epipolar Transformers","created":"2020-05-10","cited_by_count":117},{"id":"1905.00538","title":"DPSNet: End-to-end Deep Plane Sweep Stereo","created":"2019-05-02","cited_by_count":115},{"id":"2107.02191","title":"TransformerFusion: Monocular RGB Scene Reconstruction using Transformers","created":"2021-07-05","cited_by_count":106},{"id":"2004.10566","title":"Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions","created":"2020-04-22","cited_by_count":93},{"id":"1808.01900","title":"DeepTAM: Deep Tracking and Mapping","created":"2018-08-06","cited_by_count":87},{"id":"2004.02760","title":"Guiding Monocular Depth Estimation Using Depth-Attention Volume","created":"2020-04-06","cited_by_count":82},{"id":"2108.09964","title":"Learning Signed Distance Field for Multi-view Surface Reconstruction","created":"2021-08-23","cited_by_count":76},{"id":"1904.02028","title":"CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth","created":"2019-04-03","cited_by_count":75},{"id":"1810.08393","title":"DGC-Net: Dense Geometric Correspondence Network","created":"2018-10-19","cited_by_count":67},{"id":"1908.06537","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","created":"2019-08-18","cited_by_count":56},{"id":"1911.10444","title":"Normal Assisted Stereo Depth Estimation","created":"2019-11-24","cited_by_count":49},{"id":"2104.13325","title":"MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions","created":"2021-04-27","cited_by_count":43},{"id":"2102.08983","title":"Automated Detection of Equine Facial Action Units","created":"2021-02-17","cited_by_count":4}],"next_cursor":null}