College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China.
College of Mathematics and System Science, Xinjiang University, Urumqi 830046, China.
Sensors (Basel). 2022 Jan 2;22(1):329. doi: 10.3390/s22010329.
Recently, many super-resolution reconstruction (SR) feedforward networks based on deep learning have been proposed. These networks enable the reconstructed images to achieve convincing results. However, due to a large amount of computation and parameters, SR technology is greatly limited in devices with limited computing power. To trade-off the network performance and network parameters. In this paper, we propose the efficient image super-resolution network via Self-Calibrated Feature Fuse, named SCFFN, by constructing the self-calibrated feature fuse block (SCFFB). Specifically, to recover the high-frequency detail information of the image as much as possible, we propose SCFFB by self-transformation and self-fusion of features. In addition, to accelerate the network training while reducing the computational complexity of the network, we employ an attention mechanism to elaborate the reconstruction part of the network, called U-SCA. Compared with the existing transposed convolution, it can greatly reduce the computation burden of the network without reducing the reconstruction effect. We have conducted full quantitative and qualitative experiments on public datasets, and the experimental results show that the network achieves comparable performance to other networks, while we only need fewer parameters and computational resources.
最近，许多基于深度学习的超分辨率重建（SR）前馈网络被提出。这些网络使得重建图像能够达到令人信服的效果。然而，由于计算量和参数较大，SR 技术在计算能力有限的设备中受到了很大的限制。为了平衡网络性能和网络参数。在本文中，我们通过构建自校准特征融合块（SCFFB），提出了高效的图像超分辨率网络，称为 SCFFN。具体来说，为了尽可能恢复图像的高频细节信息，我们通过特征的自变换和自融合提出了 SCFFB。此外，为了在减少网络计算复杂度的同时加速网络训练，我们采用了注意力机制来详细阐述网络的重建部分，称为 U-SCA。与现有的转置卷积相比，它可以大大减少网络的计算负担，而不会降低重建效果。我们在公共数据集上进行了全面的定量和定性实验，实验结果表明，该网络在性能上与其他网络相当，而我们只需要更少的参数和计算资源。
