# Restoration of Video Frames from a Single Blurred Image with Motion Understanding

arXiv: https://arxiv.org/abs/2104.09134 · HTML: https://mlsanity.com/paper/2104.09134/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 19 Apr 2021.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [A Neural Approach to Blind Motion Deblurring](https://mlsanity.com/paper/1603.04771/) (2016)
- [Learning to Extract a Video Sequence from a Single Motion-Blurred Image](https://mlsanity.com/paper/1804.04065/) (2018)
- [Bringing Alive Blurred Moments](https://mlsanity.com/paper/1804.02913/) (2018)
- [Learning to Synthesize Motion Blur](https://mlsanity.com/paper/1811.11745/) (2018)
- [Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel](https://mlsanity.com/paper/1708.03423/) (2017)
- [Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence](https://mlsanity.com/paper/1709.05745/) (2017)
- [Motion-blurred Video Interpolation and Extrapolation](https://mlsanity.com/paper/2103.02984/) (2021)
- [Optical Flow Estimation from a Single Motion-blurred Image](https://mlsanity.com/paper/2103.02996/) (2021)
- [Stereo Video Deblurring](https://mlsanity.com/paper/1607.08421/) (2016)

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

- [Blur Interpolation Transformer for Real-World Motion from Blur](https://mlsanity.com/paper/2211.11423/) (2022)
- [Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance](https://mlsanity.com/paper/2207.10123/) (2022)
- [Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding](https://mlsanity.com/paper/2303.15417/) (2023)
- [MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video](https://mlsanity.com/paper/2312.13528/) (2023)
- [Motion Blur Decomposition with Cross-shutter Guidance](https://mlsanity.com/paper/2404.01120/) (2024)
- [Joint Flow And Feature Refinement Using Attention For Video Restoration](https://mlsanity.com/paper/2505.16434/) (2025)
- [Moment-Reenacting: Inverse Motion Degradation with Cross-shutter Guidance](https://mlsanity.com/paper/2605.22423/) (2026)
- [Continuous Facial Motion Deblurring](https://mlsanity.com/paper/2207.06626/) (2022)
- [Lightweight High-Speed Photography Built on Coded Exposure and Implicit Neural Representation of Videos](https://mlsanity.com/paper/2311.13134/) (2023)
- [PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video](https://mlsanity.com/paper/2610.01279/) (2026)

## Abstract (arXiv)

We propose a novel framework to generate clean video frames from a single motion-blurred image. While a broad range of literature focuses on recovering a single image from a blurred image, in this work, we tackle a more challenging task i.e. video restoration from a blurred image. We formulate video restoration from a single blurred image as an inverse problem by setting clean image sequence and their respective motion as latent factors, and the blurred image as an observation. Our framework is based on an encoder-decoder structure with spatial transformer network modules to restore a video sequence and its underlying motion in an end-to-end manner. We design a loss function and regularizers with complementary properties to stabilize the training and analyze variant models of the proposed network. The effectiveness and transferability of our network are highlighted through a large set of experiments on two different types of datasets: camera rotation blurs generated from panorama scenes and dynamic motion blurs in high speed videos.