DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiri Matas
11/19/2017
cs.CV

Official code: KupynOrest/DeblurGAN (2,639 stars, PyTorch, last commit 2019-12-25).

Abstract

We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss . DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance. The quality of the deblurring model is also evaluated in a novel way on a real-world problem -- object detection on (de-)blurred images. The method is 5 times faster than the closest competitor -- DeepDeblur. We also introduce a novel method for generating synthetic motion blurred images from sharp ones, allowing realistic dataset augmentation. The model, code and the dataset are available at https://github.com/KupynOrest/DeblurGAN

View on arXivView PDF

Code Implementations(1)

KupynOrest/DeblurGANOfficial100%
PyTorch

Image Deblurring using Generative Adversarial Networks

2,639531HTML, PythonApr 26, 20176 years agoNOASSERTION
blurry-imagescomputer-visionconvolutional-networksconvolutional-neural-networksdeblurring+9 more

Similar Papers

Deep learning in motion deblurring: current status, benchmarks and future prospects

91% match1 repo2252024

Blind Motion Deblurring with Pixel-Wise Kernel Estimation via Kernel Prediction Networks

90% match1 repo242023

MCMS: Multi-Category Information and Multi-Scale Stripe Attention for Blind Motion Deblurring

90% match2024

ID-Blau: Image Deblurring by Implicit Diffusion-Based reBLurring AUgmentation

89% match1 repo592023

Generalizing Event-Based Motion Deblurring in Real-World Scenarios

89% match1 repo472023

SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams

89% match1 repo262024

Cite this paper

@article{kupyn2017deblurgan,
  title  = {DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks},
  author = {Orest Kupyn and Volodymyr Budzan and Mykola Mykhailych and Dmytro Mishkin and Jiri Matas},
  year   = {2017},
  eprint = {1711.07064},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1711.07064}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1711.07064.svg)](https://codeofpaper.com/paper/1711.07064)

Discussion