Modifications to GANs using non-local attention blocks, residual connections, combined losses, and edge feedback are proposed and tested for supervised blind image deblurring.
Deep Generative Filter for Motion Deblurring
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
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.
fields
eess.IV 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
Survey of deep learning architectures for blind deblurring with PSNR and SSIM benchmarks on GOPRO and Kohler datasets.
citing papers explorer
-
Blind Deblurring Using GANs
Modifications to GANs using non-local attention blocks, residual connections, combined losses, and edge feedback are proposed and tested for supervised blind image deblurring.
-
Blind Deblurring using Deep Learning: A Survey
Survey of deep learning architectures for blind deblurring with PSNR and SSIM benchmarks on GOPRO and Kohler datasets.