Time accelerated image super-resolution using shallow residual feature representative network
This work addresses efficiency issues in image super-resolution for applications requiring fast processing, though it appears incremental as it builds on existing residual network concepts.
The paper tackles the computational complexity and time of deep convolutional neural networks for single image super-resolution by developing a shallow residual feature representative network (SRFRN), which achieves superior performance on higher scales and faster execution time compared to existing approaches.
The recent advances in deep learning indicate significant progress in the field of single image super-resolution. With the advent of these techniques, high-resolution image with high peak signal to noise ratio (PSNR) and excellent perceptual quality can be reconstructed. The major challenges associated with existing deep convolutional neural networks are their computational complexity and time; the increasing depth of the networks, often result in high space complexity. To alleviate these issues, we developed an innovative shallow residual feature representative network (SRFRN) that uses a bicubic interpolated low-resolution image as input and residual representative units (RFR) which include serially stacked residual non-linear convolutions. Furthermore, the reconstruction of the high-resolution image is done by combining the output of the RFR units and the residual output from the bicubic interpolated LR image. Finally, multiple experiments have been performed on the benchmark datasets and the proposed model illustrates superior performance for higher scales. Besides, this model also exhibits faster execution time compared to all the existing approaches.