{"list":"other","total":84,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2003.04618","title":"Convolutional Occupancy Networks","created":"2020-03-10","cited_by_count":761},{"id":"1711.10275","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","created":"2017-11-28","cited_by_count":748},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"2101.10994","title":"Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes","created":"2021-01-26","cited_by_count":426},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2006.13566","title":"DISK: Learning local features with policy gradient","created":"2020-06-24","cited_by_count":312},{"id":"1603.09114","title":"LIFT: Learned Invariant Feature Transform","created":"2016-03-30","cited_by_count":306},{"id":"1706.07567","title":"Sampling Matters in Deep Embedding Learning","created":"2017-06-23","cited_by_count":285},{"id":"2104.00681","title":"NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video","created":"2021-04-01","cited_by_count":241},{"id":"2111.13152","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","created":"2021-11-25","cited_by_count":227},{"id":"2003.01587","title":"Image Matching across Wide Baselines: From Paper to Practice","created":"2020-03-03","cited_by_count":225},{"id":"1705.10872","title":"Working hard to know your neighbor's margins: Local descriptor learning loss","created":"2017-05-30","cited_by_count":212},{"id":"1906.06195","title":"R2D2: Repeatable and Reliable Detector and Descriptor","created":"2019-06-14","cited_by_count":207},{"id":"2003.10432","title":"Atlas: End-to-End 3D Scene Reconstruction from Posed Images","created":"2020-03-23","cited_by_count":206},{"id":"1811.08188","title":"Orthographic Feature Transform for Monocular 3D Object Detection","created":"2018-11-20","cited_by_count":202},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"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":"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":"1912.05909","title":"MAGSAC++, a fast, reliable and accurate robust estimator","created":"2019-12-11","cited_by_count":161},{"id":"1908.04964","title":"Learning Two-View Correspondences and Geometry Using Order-Aware Network","created":"2019-08-14","cited_by_count":149},{"id":"2011.05499","title":"Unsupervised Learning of Dense Visual Representations","created":"2020-11-11","cited_by_count":147},{"id":"1904.05019","title":"SOSNet: Second Order Similarity Regularization for Local Descriptor Learning","created":"2019-04-10","cited_by_count":131},{"id":"2003.10071","title":"ASLFeat: Learning Local Features of Accurate Shape and Localization","created":"2020-03-23","cited_by_count":130},{"id":"1905.04132","title":"Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses","created":"2019-05-10","cited_by_count":129},{"id":"2206.07959","title":"Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?","created":"2022-06-16","cited_by_count":128},{"id":"2005.03860","title":"Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching","created":"2020-05-08","cited_by_count":126},{"id":"2203.09645","title":"MatchFormer: Interleaving Attention in Transformers for Feature Matching","created":"2022-03-17","cited_by_count":126},{"id":"2110.00966","title":"Translating Images into Maps","created":"2021-10-03","cited_by_count":115},{"id":"2107.02191","title":"TransformerFusion: Monocular RGB Scene Reconstruction using Transformers","created":"2021-07-05","cited_by_count":106},{"id":"2004.13324","title":"Learning Feature Descriptors using Camera Pose Supervision","created":"2020-04-28","cited_by_count":104},{"id":"2210.10770","title":"LaMAR: Benchmarking Localization and Mapping for Augmented Reality","created":"2022-10-19","cited_by_count":100},{"id":"2204.04752","title":"Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image","created":"2022-04-10","cited_by_count":88},{"id":"2304.02009","title":"OrienterNet: Visual Localization in 2D Public Maps with Neural Matching","created":"2023-04-04","cited_by_count":84},{"id":"2208.14743","title":"SimpleRecon: 3D Reconstruction Without 3D Convolutions","created":"2022-08-31","cited_by_count":83},{"id":"1904.03303","title":"Revealing Scenes by Inverting Structure from Motion Reconstructions","created":"2019-04-05","cited_by_count":66},{"id":"2007.13867","title":"Robust Image Retrieval-based Visual Localization using Kapture","created":"2020-07-27","cited_by_count":66},{"id":"2110.11325","title":"Learning 3D Semantic Segmentation with only 2D Image Supervision","created":"2021-10-21","cited_by_count":60},{"id":"2110.11403","title":"SCENIC: A JAX Library for Computer Vision Research and Beyond","created":"2021-10-18","cited_by_count":57},{"id":"1712.05773","title":"Semantic Visual Localization","created":"2017-12-15","cited_by_count":54},{"id":"2211.12145","title":"Uncertainty-aware Vision-based Metric Cross-view Geolocalization","created":"2022-11-22","cited_by_count":54},{"id":"2203.12979","title":"Is Geometry Enough for Matching in Visual Localization?","created":"2022-03-24","cited_by_count":48},{"id":"2208.08519","title":"Visual Cross-View Metric Localization with Dense Uncertainty Estimates","created":"2022-08-17","cited_by_count":48},{"id":"1903.05572","title":"Privacy Preserving Image-Based Localization","created":"2019-03-13","cited_by_count":47},{"id":"2101.00591","title":"Progressive Correspondence Pruning by Consensus Learning","created":"2021-01-03","cited_by_count":46},{"id":"1907.00338","title":"Large-scale, real-time visual-inertial localization revisited","created":"2019-06-30","cited_by_count":45},{"id":"1912.00623","title":"Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task","created":"2019-12-02","cited_by_count":39},{"id":"1908.05547","title":"Beyond Cartesian Representations for Local Descriptors","created":"2019-08-15","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":"1904.11932","title":"GN-Net: The Gauss-Newton Loss for Multi-Weather Relocalization","created":"2019-04-26","cited_by_count":32},{"id":"2012.10902","title":"Learning to Localize Using a LiDAR Intensity Map","created":"2020-12-20","cited_by_count":28},{"id":"1908.06387","title":"Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization","created":"2019-08-18","cited_by_count":24},{"id":"2112.12785","title":"NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning","created":"2021-12-23","cited_by_count":21},{"id":"1811.01292","title":"Geometry-Aware Recurrent Neural Networks for Active Visual Recognition","created":"2018-11-03","cited_by_count":20},{"id":"2103.05086","title":"How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines","created":"2021-03-08","cited_by_count":19},{"id":"2104.03851","title":"CoCoNets: Continuous Contrastive 3D Scene Representations","created":"2021-04-08","cited_by_count":19},{"id":"2203.13296","title":"RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers","created":"2022-03-24","cited_by_count":17},{"id":"2012.01377","title":"Cross-Descriptor Visual Localization and Mapping","created":"2020-12-02","cited_by_count":15},{"id":"2006.04250","title":"AdaLAM: Revisiting Handcrafted Outlier Detection","created":"2020-06-07","cited_by_count":14},{"id":"2111.13063","title":"MegLoc: A Robust and Accurate Visual Localization Pipeline","created":"2021-11-25","cited_by_count":10},{"id":"2003.13431","title":"Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance","created":"2020-03-30","cited_by_count":6}],"next_cursor":null}