mlsanityData to 7 Oct 2026

Event-based Vision: A Survey

arXiv 1904.08405 ↗First posted 17 Apr 2019cs.CV cs.AI cs.LGcited by 1,010

Not on the map. Why?

Abstract (arXiv)

Event cameras are bio-inspired sensors that differ from conventional frame cameras: Instead of capturing images at a fixed rate, they asynchronously measure per-pixel brightness changes, and output a stream of events that encode the time, location and sign of the brightness changes. Event cameras offer attractive properties compared to traditional cameras: high temporal resolution (in the order of microseconds), very high dynamic range (140 dB vs. 60 dB), low power consumption, and high pixel bandwidth (on the order of kHz) resulting in reduced motion blur. Hence, event cameras have a large potential for robotics and computer vision in challenging scenarios for traditional cameras, such as low-latency, high speed, and high dynamic range. However, novel methods are required to process the unconventional output of these sensors in order to unlock their potential. This paper provides a comprehensive overview of the emerging field of event-based vision, with a focus on the applications and the algorithms developed to unlock the outstanding properties of event cameras. We present event cameras from their working principle, the actual sensors that are available and the tasks that they have been used for, from low-level vision (feature detection and tracking, optic flow, etc.) to high-level vision (reconstruction, segmentation, recognition). We also discuss the techniques developed to process events, including learning-based techniques, as well as specialized processors for these novel sensors, such as spiking neural networks. Additionally, we highlight the challenges that remain to be tackled and the opportunities that lie ahead in the search for a more efficient, bio-inspired way for machines to perceive and interact with the world.

Key facts. Cited by 1,010 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 83; 2022: 103; 2023: 154; 2024: 221; 2025: 236; 2026: 213.

1,010 papers.

Sort:

By area:

  1. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 297
  2. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 251
  3. 2022Recurrent Vision Transformers for Object Detection with Event Camerascited by 158
  4. 2021E-RAFT: Dense Optical Flow from Event Camerascited by 149
  5. 2023Spike-driven Transformercited by 141
  6. 2021VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flowscited by 128
  7. 2022AEGNN: Asynchronous Event-based Graph Neural Networkscited by 118
  8. 2023Delivering Arbitrary-Modal Semantic Segmentationcited by 115
  9. 2021Event-Based Fusion for Motion Deblurring with Cross-modal Attentioncited by 112
  10. 2022Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusioncited by 110
  11. 2021Temporal-wise Attention Spiking Neural Networks for Event Streams Classificationcited by 106
  12. 2022Attention Spiking Neural Networkscited by 103
38 more
  1. 2021Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networkscited by 99
  2. 2021Learning High-Speed Flight in the Wildcited by 98
  3. 2024Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chipscited by 97
  4. 2022EventNeRF: Neural Radiance Fields from a Single Colour Event Cameracited by 92
  5. 2022Secrets of Event-Based Optical Flowcited by 92
  6. 2022Event-aided Direct Sparse Odometrycited by 91
  7. 2023Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarkscited by 90
  8. 2021Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Predictioncited by 88
  9. 2021Object Tracking by Jointly Exploiting Frame and Event Domaincited by 83
  10. 2022ESS: Learning Event-based Semantic Segmentation from Still Imagescited by 81
  11. 2024State Space Models for Event Camerascited by 75
  12. 2021Time-Ordered Recent Event (TORE) Volumes for Event Camerascited by 73
  13. 2023Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baselinecited by 73
  14. 2023GET: Group Event Transformer for Event-Based Visioncited by 73
  15. 2022E-NeRF: Neural Radiance Fields from a Moving Event Cameracited by 70
  16. 2024Recent Event Camera Innovations: A Surveycited by 67
  17. 2022Ev-NeRF: Event Based Neural Radiance Fieldcited by 59
  18. 2022Learning Dense and Continuous Optical Flow from an Event Cameracited by 59
  19. 2022Unifying Motion Deblurring and Frame Interpolation with Eventscited by 58
  20. 2023Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Reviewcited by 57
  21. 2024ReconBoost: Boosting Can Achieve Modality Reconcilementcited by 56
  22. 2024EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Imagescited by 56
  23. 2021How to Calibrate Your Event Cameracited by 53
  24. 2021Motion Deblurring with Real Eventscited by 52
  25. 2022Neuromorphic Data Augmentation for Training Spiking Neural Networkscited by 52
  26. 2023From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detectioncited by 52
  27. 2023Graph-based Asynchronous Event Processing for Rapid Object Recognitioncited by 51
  28. 2021E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognitioncited by 50
  29. 2023Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipelinecited by 50
  30. 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 47
  31. 2021EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillationcited by 46
  32. 2022HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensorscited by 46
  33. 2021Deep Learning for HDR Imaging: State-of-the-Art and Future Trendscited by 45
  34. 2022Dense Continuous-Time Optical Flow from Events and Framescited by 45
  35. 2022VECtor: A Versatile Event-Centric Benchmark for Multi-Sensor SLAMcited by 45
  36. 2023Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motioncited by 44
  37. 2023Frame-Event Alignment and Fusion Network for High Frame Rate Trackingcited by 43
  38. 2023Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackerscited by 43

50 most cited of 1,010 All 1,010 (JSON)