Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning
This work provides a more computationally efficient and accurate solution for single-image super-resolution, which is beneficial for applications with limited computational resources.
This paper addresses the computational cost of single-image super-resolution (SISR) networks by proposing a lightweight network with attentive auxiliary feature learning. The A$^2$F model achieves state-of-the-art performance across all scales with fewer than 320k parameters, outperforming existing methods.
Despite convolutional network-based methods have boosted the performance of single image super-resolution (SISR), the huge computation costs restrict their practical applicability. In this paper, we develop a computation efficient yet accurate network based on the proposed attentive auxiliary features (A$^2$F) for SISR. Firstly, to explore the features from the bottom layers, the auxiliary feature from all the previous layers are projected into a common space. Then, to better utilize these projected auxiliary features and filter the redundant information, the channel attention is employed to select the most important common feature based on current layer feature. We incorporate these two modules into a block and implement it with a lightweight network. Experimental results on large-scale dataset demonstrate the effectiveness of the proposed model against the state-of-the-art (SOTA) SR methods. Notably, when parameters are less than 320k, A$^2$F outperforms SOTA methods for all scales, which proves its ability to better utilize the auxiliary features. Codes are available at https://github.com/wxxxxxxh/A2F-SR.