{"list":"other","total":168,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"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":"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":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1506.03365","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","created":"2015-06-10","cited_by_count":1355},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"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":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"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":"1801.07791","title":"PointCNN: Convolution On $\\mathcal{X}$-Transformed Points","created":"2018-01-23","cited_by_count":764},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"1905.00889","title":"Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines","created":"2019-05-02","cited_by_count":672},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2104.06405","title":"BARF: Bundle-Adjusting Neural Radiance Fields","created":"2021-04-13","cited_by_count":642},{"id":"1607.08221","title":"MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition","created":"2016-07-27","cited_by_count":624},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2302.04264","title":"Nerfstudio: A Modular Framework for Neural Radiance Field Development","created":"2023-02-08","cited_by_count":600},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2103.12352","title":"iMAP: Implicit Mapping and Positioning in Real-Time","created":"2021-03-23","cited_by_count":476},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2012.05877","title":"INeRF: Inverting Neural Radiance Fields for Pose Estimation","created":"2020-12-10","cited_by_count":382},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"2204.05575","title":"DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection","created":"2022-04-12","cited_by_count":273},{"id":"1611.05705","title":"DSAC - Differentiable RANSAC for Camera Localization","created":"2016-11-17","cited_by_count":266},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"2212.07388","title":"NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior","created":"2022-12-14","cited_by_count":235},{"id":"1804.04610","title":"Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling","created":"2018-04-12","cited_by_count":218},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"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":"2108.13826","title":"Self-Calibrating Neural Radiance Fields","created":"2021-08-31","cited_by_count":204},{"id":"2103.09213","title":"Back to the Feature: Learning Robust Camera Localization from Pixels to Pose","created":"2021-03-16","cited_by_count":199},{"id":"2211.11738","title":"SPARF: Neural Radiance Fields from Sparse and Noisy Poses","created":"2022-11-21","cited_by_count":195},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"2112.12610","title":"PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving","created":"2021-12-23","cited_by_count":190},{"id":"2011.12172","title":"VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval","created":"2020-11-24","cited_by_count":189},{"id":"2210.13641","title":"NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields","created":"2022-10-24","cited_by_count":188},{"id":"1510.03743","title":"Wide-Area Image Geolocalization with Aerial Reference Imagery","created":"2015-10-13","cited_by_count":186},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"1903.12351","title":"Lending Orientation to Neural Networks for Cross-view Geo-localization","created":"2019-03-29","cited_by_count":180},{"id":"1709.08429","title":"DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks","created":"2017-09-25","cited_by_count":175},{"id":"1806.04807","title":"BA-Net: Dense Bundle Adjustment Network","created":"2018-06-13","cited_by_count":175},{"id":"2211.11704","title":"ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields","created":"2022-11-21","cited_by_count":158},{"id":"2103.15606","title":"GNeRF: GAN-based Neural Radiance Field without Posed Camera","created":"2021-03-29","cited_by_count":153},{"id":"1905.01489","title":"WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving","created":"2019-05-04","cited_by_count":144},{"id":"1710.01992","title":"Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks","created":"2017-10-04","cited_by_count":138},{"id":"1606.03798","title":"Deep Image Homography Estimation","created":"2016-06-13","cited_by_count":136},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135},{"id":"2011.12954","title":"RELLIS-3D Dataset: Data, Benchmarks and Analysis","created":"2020-11-17","cited_by_count":119},{"id":"2204.02296","title":"iSDF: Real-Time Neural Signed Distance Fields for Robot Perception","created":"2022-04-05","cited_by_count":109},{"id":"2011.00359","title":"TartanVO: A Generalizable Learning-based VO","created":"2020-10-31","cited_by_count":108},{"id":"1709.06841","title":"UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning","created":"2017-09-20","cited_by_count":95},{"id":"1809.08379","title":"DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments","created":"2018-09-22","cited_by_count":91},{"id":"1809.00716","title":"InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset","created":"2018-09-03","cited_by_count":87},{"id":"2204.05735","title":"GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation","created":"2022-04-12","cited_by_count":86},{"id":"1909.04866","title":"Deep Declarative Networks: A New Hope","created":"2019-09-11","cited_by_count":78},{"id":"1709.03966","title":"Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model","created":"2017-09-12","cited_by_count":75},{"id":"2212.03239","title":"Perspective Fields for Single Image Camera Calibration","created":"2022-12-06","cited_by_count":75},{"id":"2007.07527","title":"Learning to Parse Wireframes in Images of Man-Made Environments","created":"2020-07-15","cited_by_count":71},{"id":"1912.09697","title":"DeepSFM: Structure From Motion Via Deep Bundle Adjustment","created":"2019-12-20","cited_by_count":70},{"id":"1707.03167","title":"RegNet: Multimodal Sensor Registration Using Deep Neural Networks","created":"2017-07-11","cited_by_count":69},{"id":"1807.11649","title":"The Devil of Face Recognition is in the Noise","created":"2018-07-31","cited_by_count":65},{"id":"1909.05983","title":"Content-Aware Unsupervised Deep Homography Estimation","created":"2019-09-12","cited_by_count":62},{"id":"2004.02132","title":"Deep Homography Estimation for Dynamic Scenes","created":"2020-04-05","cited_by_count":61},{"id":"2106.03336","title":"Wide-Baseline Relative Camera Pose Estimation with Directional Learning","created":"2021-06-07","cited_by_count":49},{"id":"2106.12859","title":"Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images","created":"2021-06-24","cited_by_count":49},{"id":"2210.04553","title":"SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction","created":"2022-10-10","cited_by_count":49},{"id":"1712.01259","title":"A Perceptual Measure for Deep Single Image Camera Calibration","created":"2017-12-02","cited_by_count":45},{"id":"2203.15982","title":"Iterative Deep Homography Estimation","created":"2022-03-30","cited_by_count":45},{"id":"2303.04869","title":"CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation","created":"2023-03-08","cited_by_count":45},{"id":"1912.02908","title":"Why Having 10,000 Parameters in Your Camera Model is Better Than Twelve","created":"2019-12-05","cited_by_count":43},{"id":"1903.01292","title":"The StreetLearn Environment and Dataset","created":"2019-03-04","cited_by_count":42},{"id":"2103.12032","title":"Tangent Space Backpropagation for 3D Transformation Groups","created":"2021-03-22","cited_by_count":40},{"id":"2104.11693","title":"Deep Lucas-Kanade Homography for Multimodal Image Alignment","created":"2021-04-22","cited_by_count":38},{"id":"2303.10087","title":"Neural Refinement for Absolute Pose Regression with Feature Synthesis","created":"2023-03-17","cited_by_count":37},{"id":"1905.07482","title":"Learning to Reconstruct 3D Manhattan Wireframes from a Single Image","created":"2019-05-17","cited_by_count":35},{"id":"1905.02231","title":"A Geometric Approach to Obtain a Bird's Eye View from an Image","created":"2019-05-06","cited_by_count":34},{"id":"2007.09264","title":"Surface Normal Estimation of Tilted Images via Spatial Rectifier","created":"2020-07-17","cited_by_count":34}],"next_cursor":"100"}