Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Events to Enhancement: A Survey on Event-Based Imaging Technologies

Yunfan Lu, Xiaogang Xu, Pengteng Li, Yusheng Wang, Yi Cui, Huizai Yao, Hui Xiong

TL;DR

This survey synthesizes the state of event-based imaging, establishing a physical model grounded in the plenoptic function to unify how scenes are captured by event cameras versus traditional sensors. It categorizes work into enhancement and advanced imaging, detailing model-based and learning-based Event-to-Video approaches, high-temporal-resolution methods for VFI/deblurring/rolling shutter correction, and HDR/low-light strategies, while also exploring advanced tasks such as multi-view generation, light-field reconstruction, and photometric imaging. The paper identifies key challenges including data scarcity, dataset biases, sensor-noise handling, and the need for unified multi-task frameworks and hardware-software co-design. It concludes by outlining open questions and directions, emphasizing that robust, real-world, integrated imaging systems will require closer synthesis of sensor design, ISP pipelines, and foundation-model priors with event data. Collectively, the work highlights the transformative potential of events to overcome conventional imaging limits and guide future research toward practical, resilient imaging solutions.

Abstract

Event cameras offering high dynamic range and low latency have emerged as disruptive technologies in imaging. Despite growing research on leveraging these benefits for different imaging tasks, a comprehensive study of recently advances and challenges are still lacking. This limits the broader understanding of how to utilize events in universal imaging applications. In this survey, we first introduce a physical model and the characteristics of different event sensors as the foundation. Following this, we highlight the advancement and interaction of image/video enhancement tasks with events. Additionally, we explore advanced tasks, which capture richer light information with events, \eg~light field estimation, multi-view generation, and photometric. Finally, we discuss new challenges and open questions offering a perspective for this rapidly evolving field. More continuously updated resources are at this link: https://github.com/yunfanLu/Awesome-Event-Imaging

From Events to Enhancement: A Survey on Event-Based Imaging Technologies

TL;DR

This survey synthesizes the state of event-based imaging, establishing a physical model grounded in the plenoptic function to unify how scenes are captured by event cameras versus traditional sensors. It categorizes work into enhancement and advanced imaging, detailing model-based and learning-based Event-to-Video approaches, high-temporal-resolution methods for VFI/deblurring/rolling shutter correction, and HDR/low-light strategies, while also exploring advanced tasks such as multi-view generation, light-field reconstruction, and photometric imaging. The paper identifies key challenges including data scarcity, dataset biases, sensor-noise handling, and the need for unified multi-task frameworks and hardware-software co-design. It concludes by outlining open questions and directions, emphasizing that robust, real-world, integrated imaging systems will require closer synthesis of sensor design, ISP pipelines, and foundation-model priors with event data. Collectively, the work highlights the transformative potential of events to overcome conventional imaging limits and guide future research toward practical, resilient imaging solutions.

Abstract

Event cameras offering high dynamic range and low latency have emerged as disruptive technologies in imaging. Despite growing research on leveraging these benefits for different imaging tasks, a comprehensive study of recently advances and challenges are still lacking. This limits the broader understanding of how to utilize events in universal imaging applications. In this survey, we first introduce a physical model and the characteristics of different event sensors as the foundation. Following this, we highlight the advancement and interaction of image/video enhancement tasks with events. Additionally, we explore advanced tasks, which capture richer light information with events, \eg~light field estimation, multi-view generation, and photometric. Finally, we discuss new challenges and open questions offering a perspective for this rapidly evolving field. More continuously updated resources are at this link: https://github.com/yunfanLu/Awesome-Event-Imaging
Paper Structure (13 sections, 6 equations, 3 figures)

This paper contains 13 sections, 6 equations, 3 figures.

Table of Contents

  1. Introduction
  2. Physical Imaging Model and Sensors
  3. Image and Video Enhancement with Events
  4. Events to Video
  5. High Temporal Resolution of Events
  6. High Dynamic Range of Events
  7. Multi-task Joint Enhancement
  8. Advanced Imaging Tasks with Events
  9. Multi-View Generation
  10. Light Field Reconstruction
  11. Photometric Imaging
  12. Challenges & Open Questions
  13. Conclusion

Figures (3)

  • Figure 1: A diagram that summarizes this survey.
  • Figure 2: Illustration of two imaging systems combining event-based vision sensors (EVS) and active pixel sensors (APS): (a) Beam-splitter-based systems use two separate sensors, with EVS, e.g., PROPHESEE finateu20205; (b) Hybrid sensor, such as (i) Alpsentek alpsentek, (ii) SONY kodama20231, and (iii) Tianmouc yang2024vision.
  • Figure 3: (a-d) show the RGB frames and events in real scenes. (e-h) show diagrams of different degradations.