Deep models have achieved significant process on single image super-resolution (SISR) tasks, in particular large models with large kernel ($3\times3$ or more). However, the heavy computational footprint of such models prevents their deployment in real-time, resource-constrained environments. Conversely, $1\times1$ convolutions bring substantial computational efficiency, but struggle with aggregating local spatial representations, an essential capability to SISR models. In response to this dichotomy, we propose to harmonize the merits of both $3\times3$ and $1\times1$ kernels, and exploit a great potential for lightweight SISR tasks. Specifically, we propose a simple yet effective fully $1\times1$ convolutional network, named Shift-Conv-based Network (SCNet). By incorporating a parameter-free spatial-shift operation, it equips the fully $1\times1$ convolutional network with powerful representation capability while impressive computational efficiency. Extensive experiments demonstrate that SCNets, despite its fully $1\times1$ convolutional structure, consistently matches or even surpasses the performance of existing lightweight SR models that employ regular convolutions. The code and pre-trained models can be found at https://github.com/Aitical/SCNet.

翻译：深度模型在单图像超分辨率（SISR）任务上取得了显著进展，尤其大核（$3\times3$或更大）的大模型表现突出。然而，这类模型的高计算开销限制了其在实时、资源受限环境中的部署。相反，$1\times1$卷积虽能大幅提升计算效率，却难以聚合局部空间表示——这是SISR模型的关键能力。针对这一矛盾，我们提出调和$3\times3$与$1\times1$核的优势，发掘轻量化SISR任务的巨大潜力。具体而言，我们设计了一种简单而有效的全$1\times1$卷积网络——基于Shift-Conv的网络（SCNet）。通过引入无参数的空间移位操作，该网络使全$1\times1$卷积结构兼具强大的表示能力与卓越的计算效率。大量实验表明，尽管采用全$1\times1$卷积结构，SCNet仍能稳定达到甚至超越现有使用常规卷积的轻量化超分辨模型的性能。代码与预训练模型已发布于https://github.com/Aitical/SCNet。