Abstract
Recent research on single-image super-resolution (SISR) using deep convolutional neural networks has made a breakthrough and achieved tremendous performance. Despite their significant progress, numerous convolutional neural networks (CNN) are limited in practical applications, owing to the requirement of the heavy computational cost of the model. This paper proposes a multi-path network for SISR, known as multi-path deep CNN with residual inception network for single image super-resolution. In detail, a residual/ResNet block with an Inception block supports the main framework of the entire network architecture. In addition, remove the batch normalization layer from the residual network (ResNet) block and max-pooling layer from the Inception block to further reduce the number of parameters to preventing the over-fitting problem during the training. Moreover, a conventional rectified linear unit (ReLU) is replaced with Leaky ReLU activation function to speed up the training process. Specifically, we propose a novel two upscale module, which adopts three paths to upscale the features by jointly using deconvolution and upsampling layers, instead of using single deconvolution layer or upsampling layer alone. The extensive experimental results on image super-resolution (SR) using five publicly available test datasets, which show that the proposed model not only attains the higher score of peak signal-to-noise ratio/structural similarity index matrix (PSNR/SSIM) but also enables faster and more efficient calculations against the existing image SR methods. For instance, we improved our method in terms of overall PSNR on the SET5 dataset with challenging upscale factor 8× as 1.88 dB over the baseline bicubic method and reduced computational cost in terms of number of parameters 62% by deeply-recursive convolutional neural network (DRCN) method.
Highlights
Image super-resolution plays a vital role in the field of image and computer visionbased applications because the high quality or high-resolution (HR) images have more pixel density level and contains more detailed information
We suggest multi-path deep convolutional neural networks (CNN) with residual inception network for single image superresolution architecture, namely, MCISIR, which uses the residual network (ResNet) block without batch normalization (BN) layer and Inception block without the max-pooling layer to speed up the feature extraction process, as well as reduce the computational complexity of the model
The multipath schema consists of two layers such as deconvolution layer and upsampling layer to reconstruct the high quality of HR image features; Conventional deep CNN methods used the batch normalization Layer and max-pooling layer followed by the rectified linear unit (ReLU) activation function, but our approach removes both batch normalization and max-pooling layer, to reduce the computational burden of the model and the conventional ReLU activation function is replaced with the leaky ReLU activation function to avoid the vanishing gradient problem during the training efficiently
Summary
Image super-resolution plays a vital role in the field of image and computer visionbased applications because the high quality or high-resolution (HR) images have more pixel density level and contains more detailed information. Inception block still faces challenges of max-pooling layer, because it selects the maximum values of the pixel and drops other values of the feature maps To address these drawbacks, we suggest multi-path deep CNN with residual inception network for single image superresolution architecture, namely, MCISIR, which uses the ResNet block without BN layer and Inception block without the max-pooling layer to speed up the feature extraction process, as well as reduce the computational complexity of the model. The multipath schema consists of two layers such as deconvolution layer and upsampling layer to reconstruct the high quality of HR image features; Conventional deep CNN methods used the batch normalization Layer and max-pooling layer followed by the ReLU activation function, but our approach removes both batch normalization and max-pooling layer, to reduce the computational burden of the model and the conventional ReLU activation function is replaced with the leaky ReLU activation function to avoid the vanishing gradient problem during the training efficiently.
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.
