Multi-Scale Cyclic Image Deblurring Based on PVC-Resnet

Abstract

Aiming at the non-uniform blurring of image caused by optical system defects or external interference factors, such as camera shake, out-of-focus, and fast movement of object, a multi-scale cyclic image deblurring model based on a parallel void convolution-Resnet (PVC-Resnet) is proposed in this paper, in which a multi-scale recurrent network architecture and a coarse-to-fine strategy are used to restore blurred images. The backbone network is built based on Unet codec architecture, where a PVC-Resnet module designed by combinations of parallel dilated convolution and residual network is constructed in the encoder of the backbone network. The convolution receptive field is expanded with parallel dilated convolution to extract richer global features. Besides, a multi-scale feature extraction module is designed to extract the shallow features of different scale targets in blurred images, and then the extracted features are sent to the backbone network for feature refinement. The SSIM loss function and the L1 loss function are combined to construct the SSIM-L1 joint loss function for the optimization of the overall network to ensure that the image restoration at different stages can be optimized. The experimental results show that the average peak signal-to-noise ratio (PSNR) of the proposed model on different data sets is as high as 32.84 dB, and the structural similarity (SSIM) reaches 0.9235. and statistical structural similarity (Stat-SSIM) of 0.9249 on different datasets. Compared with other methods, the deblurred images generated by this method are superior to the methods proposed by Nah et al., Kupyn et al. and Cho S J et al., especially on the calibration board data set. The model proposed in this paper applies parallel dilated convolution and SSIM-L1 joint loss function to improve the performance of the network so that the edge and texture details of the restored image are clearer.

High-Resolution Image Processing of Probe-Based Confocal Laser Endomicroscopy Based on Multistage Neural Networks and Cross-Channel Attention Module

“…In the process of collecting the existing pCLE images, optical imaging systems face inherent limitations due to the physical characteristics of their components [4], encompassing factors such as the lens's shape and material, as well as the shooting location. These constraints give rise to phenomena like scattering and refraction as light traverses the lens or reflector.…”

“…For instance, Liu et al [16] proposed a novel approach that merged multilevel image restoration with the pix2pix generative adversarial network architecture within the lensless imaging sphere, which greatly improved image recovery quality in lensless systems. Zhang et al [4] proposed a multiscale circular image deblurring model based on PVC-Resnet in order to achieve the restoration of different scale objects in blurred images and obtain the global features of blurred images. Cheng et al [17] designed a method to mitigate atmospheric turbulence using optical flow and convolutional neural networks, thus reducing the turbulence mitigation problem to a deblurring problem.…”