{"total":190,"rows":[{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803,"area":null},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657,"area":null},{"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,"area":null},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404,"area":null},{"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,"area":null},{"id":"2307.14460","title":"MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation","created":"2023-07-26","cited_by_count":174,"area":null},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160,"area":null},{"id":"2203.15224","title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","created":"2022-03-29","cited_by_count":152,"area":null},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146,"area":null},{"id":"2203.11089","title":"PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark","created":"2022-03-21","cited_by_count":140,"area":null},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132,"area":null},{"id":"2209.05324","title":"Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe","created":"2022-09-12","cited_by_count":122,"area":null},{"id":"2305.05938","title":"V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting","created":"2023-05-10","cited_by_count":114,"area":null},{"id":"2106.10823","title":"3D Object Detection for Autonomous Driving: A Survey","created":"2021-06-21","cited_by_count":106,"area":null},{"id":"2307.04370","title":"Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey","created":"2023-07-10","cited_by_count":103,"area":"driving"},{"id":"2108.05249","title":"Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather","created":"2021-08-11","cited_by_count":97,"area":null},{"id":"2304.10440","title":"OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping","created":"2023-04-20","cited_by_count":83,"area":null},{"id":"2305.02008","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","created":"2023-05-03","cited_by_count":83,"area":null},{"id":"2203.13608","title":"Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task","created":"2022-03-25","cited_by_count":81,"area":null},{"id":"2303.17220","title":"Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys","created":"2023-03-30","cited_by_count":75,"area":null},{"id":"2306.09001","title":"SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving","created":"2023-06-15","cited_by_count":75,"area":null},{"id":"2106.12735","title":"Multi-Modal 3D Object Detection in Autonomous Driving: a Survey","created":"2021-06-24","cited_by_count":63,"area":null},{"id":"2403.04593","title":"Embodied Understanding of Driving Scenarios","created":"2024-03-07","cited_by_count":63,"area":"driving"},{"id":"2206.07704","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","created":"2022-06-15","cited_by_count":58,"area":null},{"id":"2304.10410","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","created":"2023-04-20","cited_by_count":58,"area":null},{"id":"2102.11585","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","created":"2021-02-23","cited_by_count":54,"area":null},{"id":"2206.02465","title":"Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning","created":"2022-06-06","cited_by_count":52,"area":null},{"id":"2509.19012","title":"Pure Vision Language Action (VLA) Models: A Comprehensive Survey","created":"2025-09-23","cited_by_count":49,"area":"mllm"},{"id":"2206.04671","title":"Open Challenges in Deep Stereo: the Booster Dataset","created":"2022-06-09","cited_by_count":48,"area":null},{"id":"2208.01166","title":"Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions","created":"2022-08-01","cited_by_count":48,"area":null},{"id":"2207.12655","title":"Semi-supervised 3D Object Detection with Proficient Teachers","created":"2022-07-26","cited_by_count":45,"area":null},{"id":"2304.02827","title":"DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Model","created":"2023-04-06","cited_by_count":43,"area":null},{"id":"2308.16714","title":"Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perception","created":"2023-08-31","cited_by_count":38,"area":null},{"id":"2110.11062","title":"Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation","created":"2021-10-21","cited_by_count":34,"area":null},{"id":"2305.18409","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","created":"2023-05-28","cited_by_count":34,"area":null},{"id":"2301.08245","title":"Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces","created":"2023-01-19","cited_by_count":33,"area":null},{"id":"2203.05056","title":"SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving","created":"2022-03-09","cited_by_count":32,"area":null},{"id":"2401.12761","title":"MUSES: The Multi-Sensor Semantic Perception Dataset for Driving under Uncertainty","created":"2024-01-23","cited_by_count":32,"area":null},{"id":"2310.15975","title":"Data-driven Traffic Simulation: A Comprehensive Review","created":"2023-10-24","cited_by_count":29,"area":null},{"id":"2407.16698","title":"Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions","created":"2024-07-23","cited_by_count":29,"area":"diffusion"},{"id":"2109.07078","title":"DSOR: A Scalable Statistical Filter for Removing Falling Snow from LiDAR Point Clouds in Severe Winter Weather","created":"2021-09-15","cited_by_count":27,"area":null},{"id":"2212.08914","title":"Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark","created":"2022-12-17","cited_by_count":26,"area":null},{"id":"2410.10738","title":"DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model","created":"2024-10-14","cited_by_count":25,"area":"wm"},{"id":"2401.08045","title":"Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities","created":"2024-01-16","cited_by_count":24,"area":"driving"},{"id":"2112.05006","title":"Exploring Event-driven Dynamic Context for Accident Scene Segmentation","created":"2021-12-09","cited_by_count":23,"area":null},{"id":"2307.07527","title":"Machine Learning for Autonomous Vehicle's Trajectory Prediction: A comprehensive survey, Challenges, and Future Research Directions","created":"2023-07-12","cited_by_count":23,"area":"driving"},{"id":"2312.03408","title":"Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future","created":"2023-12-06","cited_by_count":23,"area":null},{"id":"2204.09788","title":"SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints","created":"2022-04-20","cited_by_count":22,"area":null},{"id":"2104.13395","title":"ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception","created":"2021-04-27","cited_by_count":21,"area":null},{"id":"2108.08482","title":"VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection","created":"2021-08-19","cited_by_count":21,"area":null},{"id":"2109.03349","title":"Certifiably Optimal Outlier-Robust Geometric Perception: Semidefinite Relaxations and Scalable Global Optimization","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2208.00928","title":"OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images","created":"2022-08-01","cited_by_count":21,"area":null},{"id":"2307.10713","title":"Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV","created":"2023-07-20","cited_by_count":21,"area":null},{"id":"2311.00371","title":"Learning Cooperative Trajectory Representations for Motion Forecasting","created":"2023-11-01","cited_by_count":21,"area":null},{"id":"2303.10559","title":"Deep Learning for Camera Calibration and Beyond: A Survey","created":"2023-03-19","cited_by_count":20,"area":null},{"id":"2105.14370","title":"BAAI-VANJEE Roadside Dataset: Towards the Connected Automated Vehicle Highway technologies in Challenging Environments of China","created":"2021-05-29","cited_by_count":19,"area":null},{"id":"2406.09383","title":"Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset","created":"2024-06-13","cited_by_count":18,"area":null},{"id":"2507.17665","title":"Perspective-Invariant 3D Object Detection","created":"2025-07-23","cited_by_count":18,"area":"wm"},{"id":"2401.12888","title":"Data-Centric Evolution in Autonomous Driving: A Comprehensive Survey of Big Data System, Data Mining, and Closed-Loop Technologies","created":"2024-01-23","cited_by_count":17,"area":"driving"},{"id":"2103.03480","title":"IAFA: Instance-aware Feature Aggregation for 3D Object Detection from a Single Image","created":"2021-03-05","cited_by_count":15,"area":null},{"id":"2104.08383","title":"Optimal Pose and Shape Estimation for Category-level 3D Object Perception","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2406.19675","title":"Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey","created":"2024-06-28","cited_by_count":15,"area":null},{"id":"2407.13677","title":"PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers","created":"2024-07-18","cited_by_count":15,"area":null},{"id":"2101.05043","title":"Video action recognition for lane-change classification and prediction of surrounding vehicles","created":"2021-01-13","cited_by_count":14,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2309.04183","title":"Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality","created":"2023-09-08","cited_by_count":14,"area":null},{"id":"2204.06577","title":"OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data","created":"2022-04-13","cited_by_count":13,"area":null},{"id":"2211.06080","title":"Multi-modal Fusion Technology based on Vehicle Information: A Survey","created":"2022-11-11","cited_by_count":13,"area":null},{"id":"2312.02362","title":"PointNeRF++: A multi-scale, point-based Neural Radiance Field","created":"2023-12-04","cited_by_count":13,"area":null},{"id":"2211.10412","title":"Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey","created":"2022-11-17","cited_by_count":12,"area":null},{"id":"2304.01900","title":"PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image Diffusion","created":"2023-04-04","cited_by_count":12,"area":"diffusion"},{"id":"2304.07051","title":"The Second Monocular Depth Estimation Challenge","created":"2023-04-14","cited_by_count":12,"area":null},{"id":"2201.05761","title":"A Survey on RGB-D Datasets","created":"2022-01-15","cited_by_count":11,"area":null},{"id":"2202.01470","title":"Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth","created":"2022-02-03","cited_by_count":11,"area":null},{"id":"2202.01909","title":"Ad-datasets: a meta-collection of data sets for autonomous driving","created":"2022-02-03","cited_by_count":11,"area":null},{"id":"2211.00848","title":"Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learning","created":"2022-11-02","cited_by_count":11,"area":null},{"id":"2402.18493","title":"Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection","created":"2024-02-28","cited_by_count":11,"area":null},{"id":"2410.23780","title":"Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map","created":"2024-10-31","cited_by_count":11,"area":"driving"},{"id":"2102.10820","title":"SALT: A Semi-automatic Labeling Tool for RGB-D Video Sequences","created":"2021-02-22","cited_by_count":10,"area":null},{"id":"2210.03118","title":"Unsupervised confidence for LiDAR depth maps and applications","created":"2022-10-06","cited_by_count":10,"area":null},{"id":"2309.10815","title":"PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes","created":"2023-09-19","cited_by_count":10,"area":null},{"id":"2309.12295","title":"Learning to Drive Anywhere","created":"2023-09-21","cited_by_count":10,"area":null},{"id":"2404.16831","title":"The Third Monocular Depth Estimation Challenge","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2203.15700","title":"MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator","created":"2022-03-29","cited_by_count":9,"area":null},{"id":"2207.13050","title":"Efficient High-Resolution Deep Learning: A Survey","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2209.10174","title":"Learning Reconstructability for Drone Aerial Path Planning","created":"2022-09-21","cited_by_count":9,"area":null},{"id":"2405.09883","title":"RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception","created":"2024-05-16","cited_by_count":9,"area":null},{"id":"2208.09588","title":"Review on Action Recognition for Accident Detection in Smart City Transportation Systems","created":"2022-08-20","cited_by_count":8,"area":null},{"id":"2310.02262","title":"RSRD: A Road Surface Reconstruction Dataset and Benchmark for Safe and Comfortable Autonomous Driving","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2504.17787","title":"The Fourth Monocular Depth Estimation Challenge","created":"2025-04-24","cited_by_count":8,"area":null},{"id":"2104.04606","title":"RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes","created":"2021-04-09","cited_by_count":7,"area":null},{"id":"2109.07945","title":"Lifting 2D Object Locations to 3D by Discounting LiDAR Outliers across Objects and Views","created":"2021-09-16","cited_by_count":7,"area":null},{"id":"2109.13432","title":"Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency","created":"2021-09-28","cited_by_count":7,"area":null},{"id":"2201.05816","title":"A Critical Analysis of Image-based Camera Pose Estimation Techniques","created":"2022-01-15","cited_by_count":7,"area":null},{"id":"2206.12498","title":"Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints","created":"2022-06-24","cited_by_count":7,"area":null},{"id":"2403.01569","title":"Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV","created":"2024-03-03","cited_by_count":7,"area":null},{"id":"2405.19440","title":"MGDA Converges under Generalized Smoothness, Provably","created":"2024-05-29","cited_by_count":7,"area":null},{"id":"2407.13748","title":"General Geometry-aware Weakly Supervised 3D Object Detection","created":"2024-07-18","cited_by_count":7,"area":null},{"id":"2101.06554","title":"Diverse Complexity Measures for Dataset Curation in Self-driving","created":"2021-01-16","cited_by_count":6,"area":null},{"id":"2108.05635","title":"Memory-based Semantic Segmentation for Off-road Unstructured Natural Environments","created":"2021-08-12","cited_by_count":6,"area":null}],"next_cursor":"100"}