Lightweight and efficiency are critical drivers for the practical application
of image super-resolution (SR) algorithms. We propose a simple and effective
approach, ShuffleMixer, for lightweight image super-resolution that explores
large convolution and channel split-shuffle operation. In contrast to previous
SR models that simply stack multiple small kernel convolutions or complex
operators to learn representations, we explore a large kernel ConvNet for
mobile-friendly SR design. Specifically, we develop a large depth-wise
convolution and two projection layers based on channel splitting and shuffling
as the basic component to mix features efficiently. Since the contexts of
natural images are strongly locally correlated, using large depth-wise
convolutions only is insufficient to reconstruct fine details. To overcome this
problem while maintaining the efficiency of the proposed module, we introduce
Fused-MBConvs into the proposed network to model the local connectivity of
different features. Experimental results demonstrate that the proposed
ShuffleMixer is about 6x smaller than the state-of-the-art methods in terms of
model parameters and FLOPs while achieving competitive performance. In NTIRE
2022, our primary method won the model complexity track of the Efficient
Super-Resolution Challenge [23]. The code is available at
this https URL

本研究提出了一种轻量级的图像超分辨率算法 ShuffleMixer，其采用大型卷积和通道分割 - 混洗操作，与以前的模型不同，ShuffleMixer 采用大卷积卷积神经网络和用于 mobile-friendly 设计的 Fused-MBConvs 实现高效混特征和模拟局部图像的连续性，实验结果表明，ShuffleMixer 的模型参数和计算开销比最先进的方法小 6 倍，但性能同样出色。