Recently, convolutional neural network (CNN) based models have shown great potential in the task of single image super-resolution (SISR). However, many state-of-the-art SISR solutions are reproducing some tricks proven effective in other vision tasks, such as pursuing a deeper model. In this paper, we propose a new solution (named as Multi-Receptive-Field Network - MRFN), which outperforms existing SISR solutions in three different aspects. First, from receptive field: a novel multi-receptive-field (MRF) module is proposed to extract and fuse features in different receptive fields from local to global. Integrating these hierarchical features can generate better mappings on recovering high-fidelity details at different scales. Second, from network architectures: both dense skip connections and deep supervision are utilized to combine features from the current MRF module and preceding ones for training more representative features. Moreover, a deconvolution layer is embedded at the end of the network to avoid artificial priors induced by numerical data pre-processing (e.g., bicubic stretching), and speed up the restoration process. Finally, from error modeling: different from $L1$ and $L2$ loss functions, we proposed a novel two-parameter training loss called Weighted Huber loss function which can adaptively adjust the value of back-propagated derivative according to the residual value, thus fit the reconstruction error more effectively. Extensive qualitative and quantitative evaluation results on benchmark datasets demonstrate that our proposed MRFN can achieve more accurate recovering results than most state-of-the-art methods with significantly less complexity.

中文翻译：

---

MRFN：用于快速准确单幅图像超分辨率的多感受野网络

最近，基于卷积神经网络 (CNN) 的模型在单图像超分辨率 (SISR) 任务中显示出巨大潜力。然而，许多最先进的 SISR 解决方案正在重现一些在其他视觉任务中被证明有效的技巧，例如追求更深层次的模型。在本文中，我们提出了一种新的解决方案（称为多接收域网络 - MRFN），它在三个不同方面优于现有的 SISR 解决方案。首先，从感受野：提出了一种新颖的多感受野（MRF）模块来提取和融合从局部到全局的不同感受野中的特征。集成这些层次特征可以生成更好的映射，以恢复不同尺度的高保真细节。二、从网络架构来看：密集跳过连接和深度监督都被用来结合来自当前 MRF 模块和之前模块的特征，以训练更具代表性的特征。此外，在网络末端嵌入了一个反卷积层，以避免由数值数据预处理（例如，双三次拉伸）引起的人为先验，并加快恢复过程。最后，从误差建模：不同于$L1$和$L2$损失函数，我们提出了一种新的两参数训练损失，称为Weighted Huber损失函数，它可以根据残差值自适应调整反向传播导数的值，从而更有效地拟合重建误差。