EGARNet: adjacent residual lightweight super-resolution network based on extended group-enhanced convolution

Convolutional neural networks can solve single-image super-resolution (SR) problems owing to their powerful learning capabilities. At present, most lightweight networks are realized by stacking lightweight modules to deepen the network, which leads to the loss of flow characteristics during transmission. This paper proposes a lightweight SR network (EGARNet) based on extended group-enhanced convolution. Residual learning is introduced outside the network of cascaded lightweight modules, and adjacent residual convolution is proposed. Consequently, the shallow network features are fused by residual blocks and deep high-frequency features, which is conducive to the reconstruction of image edge structure. Our model not only reconstructs a clear edge structure but also balances the relationship between the model complexity and reconstructed image quality. The model was confirmed to be effective and lightweight using Set5, Set14, Urban100, and BSD100 test sets.

Automated summary

This paper proposes a lightweight single-image super-resolution network (EGARNet) based on extended group-enhanced convolution. By introducing residual learning and adjacent residual convolution, the shallow network features and deep high-frequency features are fused, which helps in reconstructing the image edge structure and balancing the relationship between model complexity and reconstructed image quality.