# Bringing Alive Blurred Moments

arXiv: https://arxiv.org/abs/1804.02913 · HTML: https://mlsanity.com/paper/1804.02913/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2018.

## Built on by (most cited first, 30 of 45)

- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Spatially-Adaptive Image Restoration using Distortion-Guided Networks](https://mlsanity.com/paper/2108.08617/) (2021)
- [Motion Deblurring with Real Events](https://mlsanity.com/paper/2109.13695/) (2021)
- [E-CIR: Event-Enhanced Continuous Intensity Recovery](https://mlsanity.com/paper/2203.01935/) (2022)
- [Blur Interpolation Transformer for Real-World Motion from Blur](https://mlsanity.com/paper/2211.11423/) (2022)
- [Video Frame Interpolation without Temporal Priors](https://mlsanity.com/paper/2112.01161/) (2021)
- [Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance](https://mlsanity.com/paper/2207.10123/) (2022)
- [Bringing Rolling Shutter Images Alive with Dual Reversed Distortion](https://mlsanity.com/paper/2203.06451/) (2022)
- [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)
- [Restoration of Video Frames from a Single Blurred Image with Motion Understanding](https://mlsanity.com/paper/2104.09134/) (2021)
- [Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects](https://mlsanity.com/paper/2106.08762/) (2021)
- [Learning to Super-Resolve Blurry Images with Events](https://mlsanity.com/paper/2302.13766/) (2023)
- [Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding](https://mlsanity.com/paper/2303.15417/) (2023)
- [Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding](https://mlsanity.com/paper/2105.13077/) (2021)
- [Detecting Line Segments in Motion-blurred Images with Events](https://mlsanity.com/paper/2211.07365/) (2022)
- [HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering](https://mlsanity.com/paper/2304.01686/) (2023)
- [Video Reconstruction from a Single Motion Blurred Image using Learned Dynamic Phase Coding](https://mlsanity.com/paper/2112.14768/) (2021)
- [DeblurSR: Event-Based Motion Deblurring Under the Spiking Representation](https://mlsanity.com/paper/2303.08977/) (2023)
- [Learning Parallax for Stereo Event-based Motion Deblurring](https://mlsanity.com/paper/2309.09513/) (2023)
- [Generating the Past, Present and Future from a Motion-Blurred Image](https://mlsanity.com/paper/2512.19817/) (2025)
- [Neuromorphic Synergy for Video Binarization](https://mlsanity.com/paper/2402.12644/) (2024)
- [Motion Blur Decomposition with Cross-shutter Guidance](https://mlsanity.com/paper/2404.01120/) (2024)
- [HDR Imaging for Dynamic Scenes with Events](https://mlsanity.com/paper/2404.03210/) (2024)
- [Learning Spatio-Temporal Downsampling for Effective Video Upscaling](https://mlsanity.com/paper/2203.08140/) (2022)
- [Recovering Continuous Scene Dynamics from A Single Blurry Image with Events](https://mlsanity.com/paper/2304.02695/) (2023)
- [Moment-Reenacting: Inverse Motion Degradation with Cross-shutter Guidance](https://mlsanity.com/paper/2605.22423/) (2026)
- [Affine-modeled video extraction from a single motion blurred image](https://mlsanity.com/paper/2104.03777/) (2021)
- [IR Motion Deblurring](https://mlsanity.com/paper/2111.11734/) (2021)
- [Learning to Deblur and Rotate Motion-Blurred Faces](https://mlsanity.com/paper/2112.07599/) (2021)

## Abstract (arXiv)

We present a solution for the goal of extracting a video from a single motion blurred image to sequentially reconstruct the clear views of a scene as beheld by the camera during the time of exposure. We first learn motion representation from sharp videos in an unsupervised manner through training of a convolutional recurrent video autoencoder network that performs a surrogate task of video reconstruction. Once trained, it is employed for guided training of a motion encoder for blurred images. This network extracts embedded motion information from the blurred image to generate a sharp video in conjunction with the trained recurrent video decoder. As an intermediate step, we also design an efficient architecture that enables real-time single image deblurring and outperforms competing methods across all factors: accuracy, speed, and compactness. Experiments on real scenes and standard datasets demonstrate the superiority of our framework over the state-of-the-art and its ability to generate a plausible sequence of temporally consistent sharp frames.