Ultra-high-definition display technology is widely used in broadcasting, but there is a huge contradiction between its ultra-high-resolution content and short storage. Super-Resolution (SR) can effectively alleviate this contradiction. Recently, State-of-the-art image SR approaches leveraging Deep Convolutional Neural Networks (DCNNs) have demonstrated high-quality reconstruction performance. However, most of them suffer from large model parameters, which restricts their practical application. Besides, image SR for large scaling factors ( e.g. , $\times 8$ ) is a tricky issue when the parameters diminish. To remedy these issues, we propose the Lightweight Multi-scale Aggregation Network (LMAN) for the image SR, which works well for both small and large scaling factors with limited parameters. Specifically, we propose a Group-wise Multi-scale Block (GMB) in which a group convolution is exploited for extracting and fusing multi-scale features before a channel attention layer to obtain discriminative features. Additionally, we present a novel Hierarchical Spatial Attention (HSA) mechanism to jointly and adaptively fuse local and global hierarchical features for high-resolution image reconstruction. Extensive experiments illustrate that our LMAN achieves superior performance against state-of-the-art methods with similar parameters and in particular for large scaling factors such as $4\times $ and $8\times $ .

中文翻译：

---

多尺度聚合的轻量级图像超分辨率

超高清显示技术在广电中应用广泛，但其超高分辨率的内容与短存储之间存在巨大的矛盾。超分辨率（SR）可以有效缓解这一矛盾。最近，利用深度卷积神经网络 (DCNN) 的最先进的图像 SR 方法已经证明了高质量的重建性能。然而，它们中的大多数都受到模型参数大的影响，这限制了它们的实际应用。此外，大比例因子的图像SR（ 例如 , $\times 8$ ) 当参数减少时是一个棘手的问题。为了解决这些问题，我们为图像 SR 提出了轻量级多尺度聚合网络 (LMAN)，它适用于参数有限的小型和大型缩放因子。具体来说，我们提出了一种 Group-wise Multi-scale Block (GMB)，其中在通道注意力层之前利用组卷积来提取和融合多尺度特征以获得判别特征。此外，我们提出了一种新颖的分层空间注意 (HSA) 机制，以联合和自适应地融合局部和全局分层特征以进行高分辨率图像重建。大量实验表明，我们的 LMAN 相对于具有相似参数的最先进方法取得了卓越的性能，特别是对于大比例因子，例如 $4\times $ 和 $8\times $ .