An Effective Single-Image Super-Resolution Model Using Squeeze-and-Excitation Networks
This work addresses image quality enhancement for applications like photography or medical imaging, but it is incremental as it builds on existing deep residual and SEBlock methods.
The paper tackled single-image super-resolution by modeling channel correlations in convolutional features using squeeze-and-excitation blocks, achieving state-of-the-art performance with finer texture details.
Recent works on single-image super-resolution are concentrated on improving performance through enhancing spatial encoding between convolutional layers. In this paper, we focus on modeling the correlations between channels of convolutional features. We present an effective deep residual network based on squeeze-and-excitation blocks (SEBlock) to reconstruct high-resolution (HR) image from low-resolution (LR) image. SEBlock is used to adaptively recalibrate channel-wise feature mappings. Further, short connections between each SEBlock are used to remedy information loss. Extensive experiments show that our model can achieve the state-of-the-art performance and get finer texture details.