Efficient deep neural network for photo-realistic image super-resolution

Recent progress in deep learning-based models has improved photo-realistic (or perceptual) single-image super-resolution significantly. However, despite their powerful performance, many methods are difficult to apply to real-world applications because of the heavy computational requirements. To facilitate the use of a deep model under such demands, we focus on keeping the network efficient while maintaining its performance. In detail, we design an architecture that implements a cascading mechanism on a residual network to boost the performance with limited resources via multi-level feature fusion. In addition, our proposed model adopts group convolution and recursive schemes in order to achieve extreme efficiency. We further improve the perceptual quality of the output by employing the adversarial learning paradigm and a multi-scale discriminator approach. The performance of our method is investigated through extensive internal experiments and benchmarks using various datasets. Our results show that our models outperform the recent methods with similar complexity, for both traditional pixel-based and perception-based tasks. (C) 2022 The Authors. Published by Elsevier Ltd.

Automated summary

This study focuses on the application of deep learning models in single-image super-resolution and proposes an architecture design that enhances network performance through cascading mechanism and feature fusion. By implementing group convolution and recursive schemes, the model achieves high efficiency and improves output quality. The research shows that the method performs well in various tasks.