Super Resolution Using Segmentation-Prior Self-Attention Generative Adversarial Network
This work addresses super resolution for image processing applications, offering incremental improvements in texture quality.
The authors tackled the problem of super resolution by proposing SPSAGAN, which integrates segmentation priors and self-attention to enhance texture generation and long-distance feature relationships, achieving more realistic results than SFTGAN and ESRGAN on multiple datasets.
Convolutional Neural Network (CNN) is intensively implemented to solve super resolution (SR) tasks because of its superior performance. However, the problem of super resolution is still challenging due to the lack of prior knowledge and small receptive field of CNN. We propose the Segmentation-Piror Self-Attention Generative Adversarial Network (SPSAGAN) to combine segmentation-priors and feature attentions into a unified framework. This combination is led by a carefully designed weighted addition to balance the influence of feature and segmentation attentions, so that the network can emphasize textures in the same segmentation category and meanwhile focus on the long-distance feature relationship. We also propose a lightweight skip connection architecture called Residual-in-Residual Sparse Block (RRSB) to further improve the super-resolution performance and save computation. Extensive experiments show that SPSAGAN can generate more realistic and visually pleasing textures compared to state-of-the-art SFTGAN and ESRGAN on many SR datasets.