{"list":"other","total":134,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"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":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"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":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"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":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"1906.07165","title":"High Speed and High Dynamic Range Video with an Event Camera","created":"2019-06-15","cited_by_count":345},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"2103.06011","title":"DSEC: A Stereo Event Camera Dataset for Driving Scenarios","created":"2021-03-10","cited_by_count":303},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275},{"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":"1904.06587","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","created":"2019-04-13","cited_by_count":244},{"id":"1903.04025","title":"Group-wise Correlation Stereo Network","created":"2019-03-10","cited_by_count":235},{"id":"2004.09548","title":"AANet: Adaptive Aggregation Network for Efficient Stereo Matching","created":"2020-04-20","cited_by_count":202},{"id":"2203.11483","title":"Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation","created":"2022-03-22","cited_by_count":197},{"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":"2303.06615","title":"Iterative Geometry Encoding Volume for Stereo Matching","created":"2023-03-12","cited_by_count":190},{"id":"1906.06310","title":"Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving","created":"2019-06-14","cited_by_count":188},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172},{"id":"2010.13501","title":"Hierarchical Neural Architecture Search for Deep Stereo Matching","created":"2020-10-26","cited_by_count":166},{"id":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166},{"id":"2104.04314","title":"CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching","created":"2021-04-09","cited_by_count":154},{"id":"1510.05970","title":"Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches","created":"2015-10-20","cited_by_count":151},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148},{"id":"1810.02695","title":"Learning Depth with Convolutional Spatial Propagation Network","created":"2018-10-04","cited_by_count":136},{"id":"2203.02146","title":"Attention Concatenation Volume for Accurate and Efficient Stereo Matching","created":"2022-03-04","cited_by_count":130},{"id":"1912.06704","title":"Hierarchical Deep Stereo Matching on High-resolution Images","created":"2019-12-13","cited_by_count":126},{"id":"2012.00726","title":"RAFT-3D: Scene Flow using Rigid-Motion Embeddings","created":"2020-12-01","cited_by_count":122},{"id":"2007.12140","title":"HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching","created":"2020-07-23","cited_by_count":120},{"id":"2104.03866","title":"SMD-Nets: Stereo Mixture Density Networks","created":"2021-04-08","cited_by_count":120},{"id":"1909.05845","title":"DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch","created":"2019-09-12","cited_by_count":114},{"id":"1911.13287","title":"Domain-invariant Stereo Matching Networks","created":"2019-11-29","cited_by_count":109},{"id":"2403.00486","title":"Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching","created":"2024-03-01","cited_by_count":99},{"id":"1812.06264","title":"Hierarchical Discrete Distribution Decomposition for Match Density Estimation","created":"2018-12-15","cited_by_count":93},{"id":"2006.02535","title":"A Survey on Deep Learning Techniques for Stereo-based Depth Estimation","created":"2020-06-01","cited_by_count":90},{"id":"1807.08865","title":"StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction","created":"2018-07-24","cited_by_count":88},{"id":"1807.11699","title":"SegStereo: Exploiting Semantic Information for Disparity Estimation","created":"2018-07-31","cited_by_count":88},{"id":"2108.09770","title":"MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching","created":"2021-08-22","cited_by_count":82},{"id":"1810.05424","title":"Real-time self-adaptive deep stereo","created":"2018-10-12","cited_by_count":80},{"id":"1808.01838","title":"Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation","created":"2018-08-06","cited_by_count":69},{"id":"1708.09204","title":"Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching","created":"2017-08-30","cited_by_count":63},{"id":"2006.12797","title":"PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching","created":"2020-06-23","cited_by_count":62},{"id":"2111.10502","title":"CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation","created":"2021-11-20","cited_by_count":56},{"id":"1909.03751","title":"Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching","created":"2019-09-09","cited_by_count":55},{"id":"1810.11408","title":"Anytime Stereo Image Depth Estimation on Mobile Devices","created":"2018-10-26","cited_by_count":54},{"id":"1911.10444","title":"Normal Assisted Stereo Depth Estimation","created":"2019-11-24","cited_by_count":49},{"id":"1912.01584","title":"EventGAN: Leveraging Large Scale Image Datasets for Event Cameras","created":"2019-12-03","cited_by_count":48},{"id":"2206.04671","title":"Open Challenges in Deep Stereo: the Booster Dataset","created":"2022-06-09","cited_by_count":48},{"id":"2404.06842","title":"MoCha-Stereo: Motif Channel Attention Network for Stereo Matching","created":"2024-04-10","cited_by_count":48},{"id":"2108.05773","title":"Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation","created":"2021-08-12","cited_by_count":47},{"id":"2101.01601","title":"Bilateral Grid Learning for Stereo Matching Networks","created":"2021-01-01","cited_by_count":46},{"id":"2203.10887","title":"Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective","created":"2022-03-21","cited_by_count":46},{"id":"2303.17603","title":"NeRF-Supervised Deep Stereo","created":"2023-03-30","cited_by_count":46},{"id":"2008.01484","title":"Learning Stereo from Single Images","created":"2020-08-04","cited_by_count":45},{"id":"2204.00179","title":"GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature","created":"2022-04-01","cited_by_count":43},{"id":"2403.11193","title":"Neural Markov Random Field for Stereo Matching","created":"2024-03-17","cited_by_count":40},{"id":"2201.02263","title":"ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks","created":"2022-01-06","cited_by_count":39},{"id":"1910.12361","title":"SENSE: a Shared Encoder Network for Scene-flow Estimation","created":"2019-10-27","cited_by_count":38},{"id":"2007.03085","title":"Wasserstein Distances for Stereo Disparity Estimation","created":"2020-07-06","cited_by_count":38},{"id":"2210.11719","title":"Context-Enhanced Stereo Transformer","created":"2022-10-21","cited_by_count":37},{"id":"2307.14071","title":"Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching","created":"2023-07-26","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":"2004.02138","title":"Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching","created":"2020-04-05","cited_by_count":36},{"id":"1807.06009","title":"ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems","created":"2018-07-16","cited_by_count":35},{"id":"2005.07274","title":"Bi3D: Stereo Depth Estimation via Binary Classifications","created":"2020-05-14","cited_by_count":34},{"id":"2008.07130","title":"Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation","created":"2020-08-17","cited_by_count":34},{"id":"2301.08245","title":"Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces","created":"2023-01-19","cited_by_count":33},{"id":"1803.05196","title":"EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching","created":"2018-03-14","cited_by_count":32},{"id":"2010.07347","title":"Matching-space Stereo Networks for Cross-domain Generalization","created":"2020-10-14","cited_by_count":32},{"id":"2112.01011","title":"Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks","created":"2021-12-02","cited_by_count":32},{"id":"2003.10758","title":"FADNet: A Fast and Accurate Network for Disparity Estimation","created":"2020-03-24","cited_by_count":31},{"id":"2004.04627","title":"AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching","created":"2020-04-09","cited_by_count":31},{"id":"2104.07516","title":"A Decomposition Model for Stereo Matching","created":"2021-04-15","cited_by_count":25},{"id":"2308.00728","title":"ELFNet: Evidential Local-global Fusion for Stereo Matching","created":"2023-08-01","cited_by_count":25},{"id":"1910.00541","title":"Real-Time Semantic Stereo Matching","created":"2019-10-01","cited_by_count":23},{"id":"2007.05233","title":"Continual Adaptation for Deep Stereo","created":"2020-07-10","cited_by_count":23},{"id":"2101.00431","title":"On the confidence of stereo matching in a deep-learning era: a quantitative evaluation","created":"2021-01-02","cited_by_count":23},{"id":"2304.00152","title":"Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation","created":"2023-03-31","cited_by_count":23},{"id":"2011.08332","title":"EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation","created":"2020-11-16","cited_by_count":22},{"id":"2307.16509","title":"Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matching","created":"2023-07-31","cited_by_count":22},{"id":"2005.01927","title":"StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching","created":"2020-05-05","cited_by_count":21},{"id":"2011.13117","title":"Polka Lines: Learning Structured Illumination and Reconstruction for Active Stereo","created":"2020-11-26","cited_by_count":21},{"id":"2110.15367","title":"Neural Disparity Refinement for Arbitrary Resolution Stereo","created":"2021-10-28","cited_by_count":20},{"id":"2306.15612","title":"Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching","created":"2023-06-27","cited_by_count":19}],"next_cursor":"100"}