{"total":303,"rows":[{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692,"area":null},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395,"area":null},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365,"area":null},{"id":"2109.12894","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","created":"2021-09-27","cited_by_count":259,"area":null},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159,"area":null},{"id":"2108.10552","title":"E-RAFT: Dense Optical Flow from Event Cameras","created":"2021-08-24","cited_by_count":152,"area":null},{"id":"2203.17149","title":"AEGNN: Asynchronous Event-based Graph Neural Networks","created":"2022-03-31","cited_by_count":118,"area":null},{"id":"2204.07640","title":"Event-aided Direct Sparse Odometry","created":"2022-04-15","cited_by_count":92,"area":null},{"id":"2207.10022","title":"Secrets of Event-Based Optical Flow","created":"2022-07-20","cited_by_count":92,"area":null},{"id":"2302.08890","title":"Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks","created":"2023-02-17","cited_by_count":90,"area":null},{"id":"2203.10016","title":"ESS: Learning Event-based Semantic Segmentation from Still Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75,"area":null},{"id":"2408.13627","title":"Recent Event Camera Innovations: A Survey","created":"2024-08-24","cited_by_count":68,"area":null},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66,"area":null},{"id":"2211.09078","title":"Learning Dense and Continuous Optical Flow from an Event Camera","created":"2022-11-16","cited_by_count":60,"area":null},{"id":"2105.12362","title":"How to Calibrate Your Event Camera","created":"2021-05-26","cited_by_count":53,"area":null},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50,"area":null},{"id":"2301.01928","title":"Event Camera Data Pre-training","created":"2023-01-05","cited_by_count":50,"area":null},{"id":"2206.04671","title":"Open Challenges in Deep Stereo: the Booster Dataset","created":"2022-06-09","cited_by_count":48,"area":null},{"id":"2305.17852","title":"Hierarchical Neural Memory Network for Low Latency Event Processing","created":"2023-05-29","cited_by_count":47,"area":null},{"id":"2203.13674","title":"Dense Continuous-Time Optical Flow from Events and Frames","created":"2022-03-25","cited_by_count":46,"area":null},{"id":"2303.17603","title":"NeRF-Supervised Deep Stereo","created":"2023-03-30","cited_by_count":46,"area":null},{"id":"2207.01404","title":"VECtor: A Versatile Event-Centric Benchmark for Multi-Sensor SLAM","created":"2022-07-04","cited_by_count":45,"area":null},{"id":"2108.07329","title":"TUM-VIE: The TUM Stereo Visual-Inertial Event Dataset","created":"2021-08-16","cited_by_count":41,"area":null},{"id":"2212.10368","title":"Masked Event Modeling: Self-Supervised Pretraining for Event Cameras","created":"2022-12-20","cited_by_count":41,"area":null},{"id":"2209.08323","title":"RGB-Event Fusion for Moving Object Detection in Autonomous Driving","created":"2022-09-17","cited_by_count":40,"area":null},{"id":"2303.05214","title":"Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow","created":"2023-03-09","cited_by_count":39,"area":null},{"id":"2405.05259","title":"OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies","created":"2024-05-08","cited_by_count":38,"area":null},{"id":"2204.06183","title":"ViViD++: Vision for Visibility Dataset","created":"2022-04-13","cited_by_count":34,"area":null},{"id":"2404.11884","title":"Seeing Motion at Nighttime with an Event Camera","created":"2024-04-18","cited_by_count":34,"area":null},{"id":"2207.04007","title":"Event Collapse in Contrast Maximization Frameworks","created":"2022-07-08","cited_by_count":33,"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":"2302.06492","title":"Optical flow estimation from event-based cameras and spiking neural networks","created":"2023-02-13","cited_by_count":33,"area":null},{"id":"2303.07716","title":"BlinkFlow: A Dataset to Push the Limits of Event-based Optical Flow Estimation","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2204.07286","title":"Guided Co-Modulated GAN for 360{\\deg} Field of View Extrapolation","created":"2022-04-15","cited_by_count":32,"area":null},{"id":"2211.12324","title":"Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras","created":"2022-11-22","cited_by_count":32,"area":null},{"id":"2303.11629","title":"TMA: Temporal Motion Aggregation for Event-based Optical Flow","created":"2023-03-21","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":"2205.03467","title":"EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow, Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with Monocular or Stereo Algorithms","created":"2022-05-06","cited_by_count":31,"area":null},{"id":"2211.13726","title":"Lightweight Event-based Optical Flow Estimation via Iterative Deblurring","created":"2022-11-24","cited_by_count":31,"area":null},{"id":"2307.15942","title":"CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation","created":"2023-07-29","cited_by_count":30,"area":null},{"id":"2112.06242","title":"Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical Flow","created":"2021-12-12","cited_by_count":28,"area":null},{"id":"2407.12582","title":"Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection","created":"2024-07-17","cited_by_count":28,"area":null},{"id":"2412.00832","title":"EventGPT: Event Stream Understanding with Multimodal Large Language Models","created":"2024-12-01","cited_by_count":28,"area":"mllm"},{"id":"2303.11011","title":"Learning Optical Flow from Event Camera with Rendered Dataset","created":"2023-03-20","cited_by_count":26,"area":null},{"id":"2309.15082","title":"RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation","created":"2023-09-26","cited_by_count":26,"area":null},{"id":"2211.10754","title":"HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities","created":"2022-11-19","cited_by_count":25,"area":null},{"id":"2309.08891","title":"V2CE: Video to Continuous Events Simulator","created":"2023-09-16","cited_by_count":25,"area":null},{"id":"2412.06647","title":"Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset","created":"2024-12-09","cited_by_count":25,"area":"moe"},{"id":"2109.00210","title":"EventPoint: Self-Supervised Interest Point Detection and Description for Event-based Camera","created":"2021-09-01","cited_by_count":24,"area":null},{"id":"2305.00434","title":"EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction","created":"2023-04-30","cited_by_count":24,"area":null},{"id":"2311.17286","title":"LEOD: Label-Efficient Object Detection for Event Cameras","created":"2023-11-29","cited_by_count":24,"area":null},{"id":"2403.19976","title":"eTraM: Event-based Traffic Monitoring Dataset","created":"2024-03-29","cited_by_count":24,"area":null},{"id":"2407.10802","title":"Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation","created":"2024-07-15","cited_by_count":24,"area":null},{"id":"2407.07816","title":"A Survey on Deep Stereo Matching in the Twenties","created":"2024-07-10","cited_by_count":23,"area":null},{"id":"2207.10494","title":"Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion","created":"2022-07-21","cited_by_count":21,"area":null},{"id":"2311.11533","title":"Event Camera Data Dense Pre-training","created":"2023-11-20","cited_by_count":21,"area":null},{"id":"2205.09383","title":"Emergent Visual Sensors for Autonomous Vehicles","created":"2022-05-19","cited_by_count":19,"area":null},{"id":"2209.11741","title":"Adaptive-SpikeNet: Event-based Optical Flow Estimation using Spiking Neural Networks with Learnable Neuronal Dynamics","created":"2022-09-21","cited_by_count":19,"area":null},{"id":"2409.17680","title":"Event-based Stereo Depth Estimation: A Survey","created":"2024-09-26","cited_by_count":19,"area":null},{"id":"2203.14672","title":"Are High-Resolution Event Cameras Really Needed?","created":"2022-03-28","cited_by_count":18,"area":null},{"id":"2110.04988","title":"Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception","created":"2021-10-11","cited_by_count":17,"area":null},{"id":"2304.09793","title":"Event-based Simultaneous Localization and Mapping: A Comprehensive Survey","created":"2023-04-19","cited_by_count":17,"area":null},{"id":"2401.02826","title":"CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras","created":"2024-01-05","cited_by_count":17,"area":null},{"id":"2410.09374","title":"ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras","created":"2024-10-12","cited_by_count":17,"area":null},{"id":"2212.07350","title":"A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework","created":"2022-12-14","cited_by_count":16,"area":null},{"id":"2311.00436","title":"Enhancing Traffic Object Detection in Variable Illumination with RGB-Event Fusion","created":"2023-11-01","cited_by_count":16,"area":null},{"id":"2311.11013","title":"Implicit Event-RGBD Neural SLAM","created":"2023-11-18","cited_by_count":16,"area":null},{"id":"2207.01009","title":"L2E: Lasers to Events for 6-DoF Extrinsic Calibration of Lidars and Event Cameras","created":"2022-07-03","cited_by_count":15,"area":null},{"id":"2210.01244","title":"Event-based Temporally Dense Optical Flow Estimation with Sequential Learning","created":"2022-10-03","cited_by_count":15,"area":null},{"id":"2307.05033","title":"Towards Anytime Optical Flow Estimation with Event Cameras","created":"2023-07-11","cited_by_count":15,"area":null},{"id":"2401.13853","title":"Dataset and Benchmark: Novel Sensors for Autonomous Vehicle Perception","created":"2024-01-24","cited_by_count":15,"area":null},{"id":"2403.07432","title":"Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow","created":"2024-03-12","cited_by_count":15,"area":null},{"id":"2404.10540","title":"SEVD: Synthetic Event-based Vision Dataset for Ego and Fixed Traffic Perception","created":"2024-04-12","cited_by_count":15,"area":null},{"id":"2509.15224","title":"Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation","created":"2025-09-18","cited_by_count":15,"area":null},{"id":"2506.23575","title":"Event-based Tiny Object Detection: A Benchmark Dataset and Baseline","created":"2025-06-30","cited_by_count":14,"area":null},{"id":"2107.04921","title":"Feature-based Event Stereo Visual Odometry","created":"2021-07-10","cited_by_count":13,"area":null},{"id":"2309.09947","title":"Deep Visual Odometry with Events and Frames","created":"2023-09-18","cited_by_count":13,"area":null},{"id":"2401.08474","title":"TUMTraf Event: Calibration and Fusion Resulting in a Dataset for Roadside Event-Based and RGB Cameras","created":"2024-01-16","cited_by_count":13,"area":null},{"id":"2404.19489","title":"EvGNN: An Event-driven Graph Neural Network Accelerator for Edge Vision","created":"2024-04-30","cited_by_count":13,"area":null},{"id":"2410.20451","title":"BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events","created":"2024-10-27","cited_by_count":13,"area":null},{"id":"2501.13707","title":"EventVL: Understand Event Streams via Multimodal Large Language Model","created":"2025-01-23","cited_by_count":13,"area":"mllm"},{"id":"2304.07051","title":"The Second Monocular Depth Estimation Challenge","created":"2023-04-14","cited_by_count":12,"area":null},{"id":"2405.14873","title":"Federated Online Adaptation for Deep Stereo","created":"2024-05-23","cited_by_count":12,"area":null},{"id":"2405.19718","title":"LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2407.10831","title":"Temporal Event Stereo via Joint Learning with Stereoscopic Flow","created":"2024-07-15","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":"2311.00434","title":"Event-based Background-Oriented Schlieren","created":"2023-11-01","cited_by_count":11,"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":"2307.08228","title":"Video Frame Interpolation with Stereo Event and Intensity Camera","created":"2023-07-17","cited_by_count":10,"area":null},{"id":"2407.10125","title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","created":"2024-07-14","cited_by_count":10,"area":null},{"id":"2412.06708","title":"FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies","created":"2024-12-09","cited_by_count":10,"area":null},{"id":"2503.17262","title":"Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras","created":"2025-03-21","cited_by_count":10,"area":null},{"id":"2503.19916","title":"EventFly: Event Camera Perception from Ground to the Sky","created":"2025-03-25","cited_by_count":10,"area":null},{"id":"2601.22054","title":"MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2109.03462","title":"Recalibrating the KITTI Dataset Camera Setup for Improved Odometry Accuracy","created":"2021-09-08","cited_by_count":9,"area":null},{"id":"2209.14915","title":"Spiking Neural Networks for event-based action recognition: A new task to understand their advantage","created":"2022-09-29","cited_by_count":9,"area":null},{"id":"2304.11857","title":"Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network","created":"2023-04-24","cited_by_count":9,"area":null},{"id":"2312.11911","title":"EVI-SAM: Robust, Real-time, Tightly-coupled Event-Visual-Inertial State Estimation and 3D Dense Mapping","created":"2023-12-19","cited_by_count":9,"area":null},{"id":"2403.00416","title":"Data-efficient Event Camera Pre-training via Disentangled Masked Modeling","created":"2024-03-01","cited_by_count":9,"area":null}],"next_cursor":"100"}