Deep Generative Filter for Motion Deblurring

TL;DR

This paper introduces a deep GAN-based filter with skip connections for motion deblurring, effectively removing spatially varying blur without kernel estimation, and outperforms existing methods in speed and accuracy.

Contribution

A novel deep generative filter architecture that bypasses kernel estimation, reducing test time and improving deblurring performance on benchmark datasets.

Findings

Outperforms state-of-the-art blind deblurring algorithms quantitatively.

Outperforms state-of-the-art blind deblurring algorithms qualitatively.

Reduces test time significantly for practical applications.

Abstract

Removing blur caused by camera shake in images has always been a challenging problem in computer vision literature due to its ill-posed nature. Motion blur caused due to the relative motion between the camera and the object in 3D space induces a spatially varying blurring effect over the entire image. In this paper, we propose a novel deep filter based on Generative Adversarial Network (GAN) architecture integrated with global skip connection and dense architecture in order to tackle this problem. Our model, while bypassing the process of blur kernel estimation, significantly reduces the test time which is necessary for practical applications. The experiments on the benchmark datasets prove the effectiveness of the proposed method which outperforms the state-of-the-art blind deblurring algorithms both quantitatively and qualitatively.