SOTAVerified

DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

2017-11-19CVPR 2018Code Available0· sign in to hype

Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiri Matas

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
RealBlur-J (trained on GoPro)DeblurGANSSIM (sRGB)0.83Unverified
RealBlur-R (trained on GoPro)DeblurGANSSIM (sRGB)0.9Unverified
REDSDeblurGANAverage PSNR24.09Unverified

Reproductions