Deep convolutional neural networks (CNNs) have been popularly adopted in image super-resolution (SR). However, deep CNNs for SR often suffer from the instability of training, resulting in poor image SR performance. Gathering complementary contextual information can effectively overcome the problem. Along this line, we propose a coarse-to-fine SR CNN (CFSRCNN) to recover a high-resolution (HR) image from its low-resolution version. The proposed CFSRCNN consists of a stack of feature extraction blocks (FEBs), an enhancement block (EB), a construction block (CB) and, a feature refinement block (FRB) to learn a robust SR model. Specifically, the stack of FEBs learns the long- and short-path features, and then fuses the learned features by expending the effect of the shallower layers to the deeper layers to improve the representing power of learned features. A compression unit is then used in each FEB to distill important information of features so as to reduce the number of parameters. Subsequently, the EB utilizes residual learning to integrate the extracted features to prevent from losing edge information due to repeated distillation operations. After that, the CB applies the global and local LR features to obtain coarse features, followed by the FRB to refine the features to reconstruct a high-resolution image. Extensive experiments demonstrate the high efficiency and good performance of our CFSRCNN model on benchmark datasets compared with state-of-the-art SR models. The code of CFSRCNN is accessible on https://github.com/hellloxiaotian/CFSRCNN.

中文翻译：

---

用于图像超分辨率的粗到细 CNN

深度卷积神经网络 (CNN) 已广泛用于图像超分辨率 (SR)。然而，用于 SR 的深度 CNN 经常遭受训练的不稳定性，导致图像 SR 性能不佳。收集互补的上下文信息可以有效地克服这个问题。沿着这条路线，我们提出了一种从粗到细的 SR CNN (CFSRCNN) 来从其低分辨率版本中恢复高分辨率 (HR) 图像。所提出的 CFSRCNN 由一堆特征提取块 (FEB)、一个增强块 (EB)、一个构造块 (CB) 和一个特征细化块 (FRB) 组成，以学习稳健的 SR 模型。具体来说，FEB 堆栈学习长路径和短路径特征，然后通过将较浅层的效果扩展到较深层来融合学习到的特征，以提高学习到的特征的表示能力。然后在每个FEB中使用压缩单元来提取特征的重要信息，从而减少参数的数量。随后，EB 利用残差学习来整合提取的特征，以防止由于重复蒸馏操作而丢失边缘信息。之后，CB 应用全局和局部 LR 特征来获得粗特征，然后是 FRB 来细化特征以重建高分辨率图像。大量实验证明，与最先进的 SR 模型相比，我们的 CFSRCNN 模型在基准数据集上的高效率和良好性能。CFSRCNN 的代码可在 https://github 上访问。