In recent years, deep models have achieved great success in the field of single-image super-resolution (SISR) by incorporating a large number of parameters to obtain satisfactory performance. However, this achievement typically gives rise to high computational complexity, which greatly restricts deep SISR applications in deployment on mobile devices with limited computation and storage resources. To address this problem, in this article, we propose a flexibly adjustable super-lightweight SISR pipeline: s-LWSR. First, to efficiently abstract features from low-resolution images, we design a highly efficient U-shaped backbone, along with an information pool, which is constructed to mix multilevel information from the first half of our pipeline. Second, a compression mechanism based on depthwise-separable convolution is employed to further reduce the number of parameters with a negligible degradation in performance. Third, by revealing the specific role of activation in many deep models, we remove several activation layers in our super-resolution (SR) model to retain useful information, leading to a further improvement in the final performance. Extensive experiments demonstrate that our s-LWSR, with limited parameters and operations, can achieve a similar performance to that of other cumbersome but state-of-the-art (SOTA) deep SR methods.

中文翻译：

---

s-LWSR：超轻量级超高分辨率网络。

近年来，深度模型通过合并大量参数以获得令人满意的性能，在单图像超分辨率（SISR）领域取得了巨大成功。但是，这种成就通常会导致很高的计算复杂度，从而极大地限制了深度SISR应用程序在计算和存储资源有限的移动设备上的部署。为了解决这个问题，在本文中，我们提出了一个可灵活调整的超轻型SISR管道：s-LWSR。首先，为了有效地从低分辨率图像中提取特征，我们设计了一个高效的U形主干以及一个信息池，该信息池用于混合来自管道前半部分的多级信息。第二，采用基于深度可分离的卷积的压缩机制来进一步减少参数数量，而性能却可以忽略不计。第三，通过揭示激活在许多深度模型中的特定作用，我们在超分辨率（SR）模型中删除了几个激活层以保留有用的信息，从而进一步改善了最终性能。大量实验表明，我们的s-LWSR具有有限的参数和操作，可以实现与其他繁琐但最新的（SRA）深层SR方法相似的性能。从而导致最终效果的进一步改善。大量实验表明，我们的s-LWSR具有有限的参数和操作，可以实现与其他繁琐但最新的（SRA）深层SR方法相似的性能。从而导致最终效果的进一步改善。大量实验表明，我们的s-LWSR具有有限的参数和操作，可以实现与其他繁琐但最新的（SRA）深层SR方法相似的性能。