Deep Generative Filter for Motion Deblurring
This addresses the problem of camera shake blur for computer vision applications, offering a practical solution with faster processing, but it is incremental as it builds on existing GAN-based approaches.
The paper tackles motion deblurring in images by proposing a deep generative filter based on GAN architecture, which bypasses blur kernel estimation to reduce test time and outperforms state-of-the-art blind deblurring methods on benchmark datasets.
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.