# Event-based Image Deblurring with Dynamic Motion Awareness

arXiv: https://arxiv.org/abs/2208.11398 · HTML: https://mlsanity.com/paper/2208.11398/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 60 references that are in the map.
- First posted on arXiv 24 Aug 2022.

## Builds on (most cited first, 30 of 32)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Events-to-Video: Bringing Modern Computer Vision to Event Cameras](https://mlsanity.com/paper/1904.08298/) (2019)
- [Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal](https://mlsanity.com/paper/1503.00593/) (2015)
- [Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera](https://mlsanity.com/paper/1811.10180/) (2018)
- [Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring](https://mlsanity.com/paper/2004.05343/) (2020)
- [Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training](https://mlsanity.com/paper/1911.07410/) (2019)
- [From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur](https://mlsanity.com/paper/1612.02583/) (2016)
- [Learning Event-Based Motion Deblurring](https://mlsanity.com/paper/2004.05794/) (2020)
- [Event Enhanced High-Quality Image Recovery](https://mlsanity.com/paper/2007.08336/) (2020)
- [Mobile Computational Photography: A Tour](https://mlsanity.com/paper/2102.09000/) (2021)
- [Explore Image Deblurring via Blur Kernel Space](https://mlsanity.com/paper/2104.00317/) (2021)
- [Learning to Extract a Video Sequence from a Single Motion-Blurred Image](https://mlsanity.com/paper/1804.04065/) (2018)
- [Motion Deblurring with Real Events](https://mlsanity.com/paper/2109.13695/) (2021)
- [Learning Blind Motion Deblurring](https://mlsanity.com/paper/1708.04208/) (2017)
- [Learning to Deblur and Generate High Frame Rate Video with an Event Camera](https://mlsanity.com/paper/2003.00847/) (2020)
- [Motion Deblurring in the Wild](https://mlsanity.com/paper/1701.01486/) (2017)

## Built on by (most cited first, 10 of 10)

- [HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks](https://mlsanity.com/paper/2305.06382/) (2023)
- [Mitigating Motion Blur in Neural Radiance Fields with Events and Frames](https://mlsanity.com/paper/2403.19780/) (2024)
- [A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild](https://mlsanity.com/paper/2301.05191/) (2023)
- [Low-Light Image Enhancement using Event-Based Illumination Estimation](https://mlsanity.com/paper/2504.09379/) (2025)
- [Deep learning in motion deblurring: current status, benchmarks and future prospects](https://mlsanity.com/paper/2401.05055/) (2024)
- [Deformable Convolutions and LSTM-based Flexible Event Frame Fusion Network for Motion Deblurring](https://mlsanity.com/paper/2306.00834/) (2023)
- [Event-based Motion Deblurring via Multi-Temporal Granularity Fusion](https://mlsanity.com/paper/2412.11866/) (2024)
- [Restoring Real-World Degraded Events Improves Deblurring Quality](https://mlsanity.com/paper/2407.20502/) (2024)
- [Passive Non-Line-of-Sight Imaging with Light Transport Modulation](https://mlsanity.com/paper/2312.16014/) (2023)
- [EvDiff: Event-Based Video Reconstruction using One-Step Diffusion Models](https://mlsanity.com/paper/2511.17492/) (2025)

## Abstract (arXiv)

Non-uniform image deblurring is a challenging task due to the lack of temporal and textural information in the blurry image itself. Complementary information from auxiliary sensors such event sensors are being explored to address these limitations. The latter can record changes in a logarithmic intensity asynchronously, called events, with high temporal resolution and high dynamic range. Current event-based deblurring methods combine the blurry image with events to jointly estimate per-pixel motion and the deblur operator. In this paper, we argue that a divide-and-conquer approach is more suitable for this task. To this end, we propose to use modulated deformable convolutions, whose kernel offsets and modulation masks are dynamically estimated from events to encode the motion in the scene, while the deblur operator is learned from the combination of blurry image and corresponding events. Furthermore, we employ a coarse-to-fine multi-scale reconstruction approach to cope with the inherent sparsity of events in low contrast regions. Importantly, we introduce the first dataset containing pairs of real RGB blur images and related events during the exposure time. Our results show better overall robustness when using events, with improvements in PSNR by up to 1.57dB on synthetic data and 1.08 dB on real event data.