Abstract
The main target of Single image super-resolution is to recover high-quality or high-resolution image from degraded version of low-quality or low-resolution image. Recently, deep learning-based approaches have achieved significant performance in image super-resolution tasks. However, existing approaches related with image super-resolution fail to use the features information of low-resolution images as well as do not recover the hierarchical features for the final reconstruction purpose. In this research work, we have proposed a new architecture inspired by ResNet and Xception networks, which enable a significant drop in the number of network parameters and improve the processing speed to obtain the SR results. We are compared our proposed algorithm with existing state-of-the-art algorithms and confirmed the great ability to construct HR images with fine, rich, and sharp texture details as well as edges. The experimental results validate that our proposed approach has robust performance compared to other popular techniques related to accuracy, speed, and visual quality.
Highlights
Single image super-resolution (SISR) is more attractive in recovering the high-resolution (HR) output image from a degraded version of a low-resolution (LR) input image generating by a cheaper cost imaging framework within the limited environmental conditions
Our initial feature extraction stage consists of one convolution layer and two ResNet Blocks with skip connection followed by Parametric Rectified Linear Unit (PReLU) [71] activation function
Yang et al [23] and the Berkeley Segmentation Dataset (BSD300) [82] are commonly used image datasets, because these datasets are used by well-known SR methods, like very deep SR network (VDSR) [32], Deeply Recursive Convolutional Network for image super-resolution (DRCN) [33] and Laplacian Pyramid Super-Resolution Network (LapSRN) [44] for the training purpose
Summary
Single image super-resolution (SISR) is more attractive in recovering the high-resolution (HR) output image from a degraded version of a low-resolution (LR) input image generating by a cheaper cost imaging framework within the limited environmental conditions. Reconstruction-based image super-resolution approaches [19,20,21,22,23,24] are mostly adopted previous information to narrow-down of the feasible solution which can get the benefit of reconstructing the fine details of edges and suppress the statistical noise effects [25] These methods are time-consuming and rapidly degrading image reconstruction performance on 4× or 8× scale factor enlargements. For the purpose of solving such issues and improving the quality of the LR image, we proposed a Multi-scale Xception Based Depthwise Separable Convolution for Single Image Super-resolution (MXDSIR) to generate the HR output image from the original LR input image.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
