Deep learning has been successfully applied to the single-image super-resolution (SISR) task with superior performance in recent years. However, most convolutional neural network (CNN) based SR models have a large number of parameters to be optimized, which requires heavy computation and thereby limits their real-world applications. In this work, a novel lightweight SR network, named Adaptive Weighted Super-Resolution Network (LW-AWSRN), is proposed to address this issue. A novel local fusion block (LFB) is developed in LW-AWSRN for efficient residual learning, which consists of several stacked adaptive weighted residual units (AWRU) and a local residual fusion unit (LRFU). Moreover, an adaptive weighted multi-scale (AWMS) module is proposed to make full use of features for the reconstruction of HR images. The AWMS module includes several convolutions with multiple scales, and the redundancy scale branch can be removed according to the contribution of adaptive weights for the lightweight network. The experimental results on the commonly used datasets show that the proposed LW-AWSRN achieves superior performance on $\times$ 2, $\times$ 3, $\times$ 4, and $\times$ 8 scale factors compared to state-of-the-art methods with similar parameters and computational overhead. It suggests that LW-AWSRN has a better trade-off between reconstruction quality and model size.

近年来，深度学习已成功应用于单图像超分辨率 (SISR) 任务，并具有卓越的性能。然而，大多数基于卷积神经网络 (CNN) 的 SR 模型都有大量参数需要优化，这需要大量计算，从而限制了它们的实际应用。在这项工作中，提出了一种名为自适应加权超分辨率网络 (LW-AWSRN) 的新型轻量级 SR 网络来解决这个问题。在 LW-AWSRN 中开发了一种新的局部融合块 (LFB)，用于有效的残差学习，它由几个堆叠的自适应加权残差单元 (AWRU) 和一个局部残差融合单元 (LRFU) 组成。此外，提出了一种自适应加权多尺度（AWMS）模块，以充分利用特征来重建 HR 图像。AWMS 模块包括多个多尺度的卷积，可以根据自适应权重对轻量级网络的贡献去除冗余尺度分支。在常用数据集上的实验结果表明，所提出的 LW-AWSRN 在$\times$ 2、 $\times$ 3、 $\times$ 4，和 $\times$与具有相似参数和计算开销的最先进方法相比，有 8 个比例因子。这表明 LW-AWSRN 在重建质量和模型大小之间具有更好的权衡。