In recent years, significant progress has been made in single-image super-resolution (SISR) with the emergence of convolutional neural networks (CNNs). However, the application of SISR on low computing power devices is hindered by the massive number of parameters and computational costs. Despite the focus on lightweight SISR models in many studies, the majority still struggles to balance performance and model size, making it difficult to apply them in real-life situations. Therefore, we propose to construct an SISR network termed 3D lightweight image super-resolution (3DLSR) network by introducing 3DCNN to this task. By leveraging the additional dimension of 3D convolution, the proposed 3DLSR can extract the interchannel and innerchannel information of color images, thereby aiding the reconstruction of high-resolution images while maintaining a small model size. Furthermore, we redesign a best-fitting network structure for 3DLSR based on the difference between 3D convolution and 2D convolution. The experimental results demonstrate the superiority of our 3DLSR, as it can achieve a competitively quantitative metric with a parameter size one order of magnitude smaller than the majority, compared with the state-of-the-art methods.

中文翻译：

---

使用 3D 卷积神经网络的轻量级图像超分辨率网络

近年来，随着卷积神经网络（CNN）的出现，单图像超分辨率（SISR）取得了重大进展。然而，SISR在低计算能力设备上的应用受到大量参数和计算成本的阻碍。尽管许多研究都关注轻量级 SISR 模型，但大多数研究仍然难以平衡性能和模型大小，这使得它们很难在现实生活中应用。因此，我们建议通过将 3DCNN 引入到该任务中来构建一个称为 3D 轻量级图像超分辨率（3DLSR）网络的 SISR 网络。通过利用 3D 卷积的附加维度，所提出的 3DLSR 可以提取彩色图像的通道间和通道内信息，从而有助于高分辨率图像的重建，同时保持较小的模型尺寸。此外，我们根据3D卷积和2D卷积之间的差异，重新设计了3DLSR的最佳拟合网络结构。实验结果证明了我们的 3DLSR 的优越性，因为与最先进的方法相比，它可以实现具有竞争力的定量指标，参数大小比大多数方法小一个数量级。