DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

TL;DR

DeblurGAN is a fast, end-to-end learned motion deblurring method using conditional GANs that achieves state-of-the-art results and improves object detection on blurred images.

Contribution

It introduces DeblurGAN, a novel conditional GAN-based approach for motion deblurring, with a new synthetic data generation method and real-world evaluation.

Findings

Achieves state-of-the-art structural similarity and visual quality.

Runs 5 times faster than previous leading methods.

Enhances object detection accuracy on deblurred images.

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