# Reblur2Deblur: Deblurring Videos via Self-Supervised Learning

arXiv: https://arxiv.org/abs/1801.05117 · HTML: https://mlsanity.com/paper/1801.05117/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2018.

## Built on by (most cited first, 30 of 38)

- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications](https://mlsanity.com/paper/2211.08064/) (2022)
- [Iterative Filter Adaptive Network for Single Image Defocus Deblurring](https://mlsanity.com/paper/2108.13610/) (2021)
- [Unifying Motion Deblurring and Frame Interpolation with Events](https://mlsanity.com/paper/2203.12178/) (2022)
- [Motion Deblurring with Real Events](https://mlsanity.com/paper/2109.13695/) (2021)
- [Learning Degradation Representations for Image Deblurring](https://mlsanity.com/paper/2208.05244/) (2022)
- [MC-Blur: A Comprehensive Benchmark for Image Deblurring](https://mlsanity.com/paper/2112.00234/) (2021)
- [A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild](https://mlsanity.com/paper/2301.05191/) (2023)
- [Generalizing Event-Based Motion Deblurring in Real-World Scenarios](https://mlsanity.com/paper/2308.05932/) (2023)
- [FCL-GAN: A Lightweight and Real-Time Baseline for Unsupervised Blind Image Deblurring](https://mlsanity.com/paper/2204.07820/) (2022)
- [Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring](https://mlsanity.com/paper/2104.12665/) (2021)
- [Self-Supervised Deep Blind Video Super-Resolution](https://mlsanity.com/paper/2201.07422/) (2022)
- [Non-uniform Blur Kernel Estimation via Adaptive Basis Decomposition](https://mlsanity.com/paper/2102.01026/) (2021)
- [INFWIDE: Image and Feature Space Wiener Deconvolution Network for Non-blind Image Deblurring in Low-Light Conditions](https://mlsanity.com/paper/2207.08201/) (2022)
- [Blind Motion Deblurring with Pixel-Wise Kernel Estimation via Kernel Prediction Networks](https://mlsanity.com/paper/2308.02947/) (2023)
- [Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive](https://mlsanity.com/paper/2305.19862/) (2023)
- [Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding](https://mlsanity.com/paper/2105.13077/) (2021)
- [Physics vs. Learned Priors: Rethinking Camera and Algorithm Design for Task-Specific Imaging](https://mlsanity.com/paper/2204.09871/) (2022)
- [Deep Dynamic Scene Deblurring from Optical Flow](https://mlsanity.com/paper/2301.07329/) (2023)
- [Learning to Deblur Polarized Images](https://mlsanity.com/paper/2402.18134/) (2024)
- [Meta Transferring for Deblurring](https://mlsanity.com/paper/2210.08036/) (2022)
- [Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring](https://mlsanity.com/paper/2204.12139/) (2022)
- [Learning to See Through Dazzle](https://mlsanity.com/paper/2402.15919/) (2024)
- [Recovering Continuous Scene Dynamics from A Single Blurry Image with Events](https://mlsanity.com/paper/2304.02695/) (2023)
- [Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs](https://mlsanity.com/paper/2409.17792/) (2024)
- [Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and Deblurring](https://mlsanity.com/paper/2412.07256/) (2024)
- [Deep Camera Obscura: An Image Restoration Pipeline for Lensless Pinhole Photography](https://mlsanity.com/paper/2108.05563/) (2021)
- [Human and Scene Motion Deblurring using Pseudo-blur Synthesizer](https://mlsanity.com/paper/2111.12911/) (2021)
- [Simulator-Based Self-Supervision for Learned 3D Tomography Reconstruction](https://mlsanity.com/paper/2212.07431/) (2022)
- [Unsupervised Methods for Video Quality Improvement: A Survey of Restoration and Enhancement Techniques](https://mlsanity.com/paper/2507.08375/) (2025)

## Abstract (arXiv)

Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference. Traditional deblurring algorithms leverage the physics of the image formation model and use hand-crafted priors: they usually produce results that better reflect the underlying scene, but present artifacts. Recent learning-based methods implicitly extract the distribution of natural images directly from the data and use it to synthesize plausible images. Their results are impressive, but they are not always faithful to the content of the latent image. We present an approach that bridges the two. Our method fine-tunes existing deblurring neural networks in a self-supervised fashion by enforcing that the output, when blurred based on the optical flow between subsequent frames, matches the input blurry image. We show that our method significantly improves the performance of existing methods on several datasets both visually and in terms of image quality metrics. The supplementary material is https://goo.gl/nYPjEQ