DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

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

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Deblurring RealBlur-J (trained on GoPro) DeblurGAN SSIM (sRGB) 0.834 # 7
Deblurring RealBlur-R (trained on GoPro) DeblurGAN SSIM (sRGB) 0.903 # 12
Deblurring REDS DeblurGAN Average PSNR 24.09 # 3

Methods