mlsanityData to 7 Oct 2026

E-CIR: Event-Enhanced Continuous Intensity Recovery

arXiv 2203.01935 ↗First posted 3 Mar 2022eess.IV cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

A camera begins to sense light the moment we press the shutter button. During the exposure interval, relative motion between the scene and the camera causes motion blur, a common undesirable visual artifact. This paper presents E-CIR, which converts a blurry image into a sharp video represented as a parametric function from time to intensity. E-CIR leverages events as an auxiliary input. We discuss how to exploit the temporal event structure to construct the parametric bases. We demonstrate how to train a deep learning model to predict the function coefficients. To improve the appearance consistency, we further introduce a refinement module to propagate visual features among consecutive frames. Compared to state-of-the-art event-enhanced deblurring approaches, E-CIR generates smoother and more realistic results. The implementation of E-CIR is available at https://github.com/chensong1995/E-CIR.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 19 of its 46 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

19 of 46 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2019Quantifying the Carbon Emissions of Machine Learningcited by 516
  4. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  5. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  6. 2019High Speed and High Dynamic Range Video with an Event Cameracited by 344
  7. 2018TDAN: Temporally Deformable Alignment Network for Video Super-Resolutioncited by 225
  8. 2017Video Frame Interpolation via Adaptive Separable Convolutioncited by 211
  9. 2019Events-to-Video: Bringing Modern Computer Vision to Event Camerascited by 191
  10. 2016Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensationcited by 156
  11. 2021TimeLens: Event-based Video Frame Interpolationcited by 150
  12. 2018Bringing a Blurry Frame Alive at High Frame-Rate with an Event Cameracited by 141
7 more
  1. 2020Learning Event-Based Motion Deblurringcited by 81
  2. 2020Event Enhanced High-Quality Image Recoverycited by 68
  3. 2018Learning to Extract a Video Sequence from a Single Motion-Blurred Imagecited by 56
  4. 2021Motion Deblurring with Real Eventscited by 52
  5. 2018Bringing Alive Blurred Momentscited by 44
  6. 2020Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equationcited by 39
  7. 2019Fast Spatio-Temporal Residual Network for Video Super-Resolutioncited by 34

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 8; 2025: 4; 2026: 1.

25 papers.

Sort:

  1. 2023Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarkscited by 90
  2. 2025Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fieldscited by 24
  3. 2023Generalizing Event-Based Motion Deblurring in Real-World Scenarioscited by 20
  4. 2023Event-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurringcited by 13
  5. 2023Learning to Super-Resolve Blurry Images with Eventscited by 10
  6. 2023UniINR: Event-guided Unified Rolling Shutter Correction, Deblurring, and Interpolationcited by 9
  7. 2024SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streamscited by 6
  8. 2024HR-INR: Continuous Space-Time Video Super-Resolution via Event Cameracited by 6
  9. 2023An Asynchronous Intensity Representation for Framed and Event Video Sourcescited by 5
  10. 2023DeblurSR: Event-Based Motion Deblurring Under the Spiking Representationcited by 4
  11. 2023Neural Image Re-Exposurecited by 4
  12. 2023Learning Parallax for Stereo Event-based Motion Deblurringcited by 4
13 more
  1. 2023CrossZoom: Simultaneously Motion Deblurring and Event Super-Resolvingcited by 4
  2. 2024SpikeNVS: Enhancing Novel View Synthesis from Blurry Images via Spike Cameracited by 4
  3. 2024Revisit Event Generation Model: Self-Supervised Learning of Event-to-Video Reconstruction with Implicit Neural Representationscited by 4
  4. 2023Accelerated Event-Based Feature Detection and Compression for Surveillance Video Systemscited by 3
  5. 2024HDR Imaging for Dynamic Scenes with Eventscited by 3
  6. 2024USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splattingcited by 3
  7. 2025Event Camera Guided Visual Media Restoration & 3D Reconstruction: A Surveycited by 3
  8. 2023Recovering Continuous Scene Dynamics from A Single Blurry Image with Eventscited by 2
  9. 2025Rethinking High-speed Image Reconstruction Framework with Spike Cameracited by 1
  10. 2024Non-Uniform Exposure Imaging via Neuromorphic Shutter Controlcited by 0
  11. 2024PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyondcited by 0
  12. 2025From Events to Enhancement: A Survey on Event-Based Imaging Technologiescited by 0
  13. 2026DeLux: Cross-Modal Local Artifact Restoration in Video Using Neuromorphic Datacited by 0