Generative Adversarial Network on Motion-Blur Image Restoration

TL;DR

This paper presents a GAN-based deep learning approach for restoring motion-blurred images, demonstrating effective deblurring with quantitative improvements on the GoPro dataset and real-world applicability.

Contribution

It introduces a GAN model trained on paired blurred and clear images for motion deblurring, with quantitative evaluation showing promising results.

Findings

Achieved mean PSNR of 29.1644 and SSIM of 0.7459

Produced sharper images with good restoration effects

Average deblurring time of 4.6921 seconds

Abstract

In everyday life, photographs taken with a camera often suffer from motion blur due to hand vibrations or sudden movements. This phenomenon can significantly detract from the quality of the images captured, making it an interesting challenge to develop a deep learning model that utilizes the principles of adversarial networks to restore clarity to these blurred pixels. In this project, we will focus on leveraging Generative Adversarial Networks (GANs) to effectively deblur images affected by motion blur. A GAN-based Tensorflow model is defined, training and evaluating by GoPro dataset which comprises paired street view images featuring both clear and blurred versions. This adversarial training process between Discriminator and Generator helps to produce increasingly realistic images over time. Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) are the two evaluation metrics used to provide quantitative measures of image quality, allowing us to evaluate the effectiveness of the deblurring process. Mean PSNR in 29.1644 and mean SSIM in 0.7459 with average 4.6921 seconds deblurring time are achieved in this project. The blurry pixels are sharper in the output of GAN model shows a good image restoration effect in real world applications.