A Cascaded Convolutional Neural Network for Image Deblurring and Denoising
B M Mahendra, Savita Sonoli, Tarun Gowda · Research Square · 2022
Abstract Although noise management has received a lot ofattention recently, image deblurring is still difficult. Imageswithout any noisy pixels are the focus of the current deblurringnetworks. To explicitly or implicitly lessen the impact of noisypixels on image deblurring, existing methods primarily relyon repetitive noise detection stages. However, these iterativeoptimization procedures and heuristic operations, which aredifficult and time-consuming, are frequently used in these noisypixels detection steps. In this paper we propose a cascaded modelof two separate networks which will handle the noisy pixelswithout any reduction in image quality. Our model aims todenoise an image first and then deblur it. In addition, it wasfound that deblurring an image first, then denoising it, producedbetter results than training a deblurring network on noisy images.Numerous tests demonstrate that this cascaded network performscompetitively in terms of PSNR and SSIM.