A skip-connection learning framework-based convolution neural network (CNN) has recently achieved great success in image super-resolution (SR). However, most CNN models based on the skip-connection learning framework do not fully make use of potential multi-scale features of images. In this paper, we propose a multi-scale skip-connection network (MSN) to improve the visual quality of the image SR. First, convolution kernels with different sizes are exploited to capture the multi-scale features of LR images. All the feature-maps captured by convolution kernels of the same size are direct input into a multi-scale hybrid group (MHG); second, the convolution layers of each MHG are composed of dilated convolutions and standard convolutions. The hybrid convolutions can fully train feature details obtained from preceding and current scale convolution layers; three, the output of each hybrid convolution layer is fed into subsequent hybrid convolution layers by skip-connections, thus producing dense connections; lastly, the meta-upscale module is used as the upscale module, which can magnify the trained feature maps arbitrary scale factors. By being evaluated on a wide variety of images, the proposed MSN network achieves an advantage over the state-of-the-art methods in terms of both numerical results and visual quality.

中文翻译：

---

用于图像超分辨率的多尺度跳跃连接网络

基于跳过连接学习框架的卷积神经网络（CNN）最近在图像超分辨率（SR）方面取得了巨大成功。然而，大多数基于跳过连接学习框架的 CNN 模型并没有充分利用图像的潜在多尺度特征。在本文中，我们提出了一种多尺度跳跃连接网络（MSN）来提高图像 SR 的视觉质量。首先，利用不同大小的卷积核来捕捉 LR 图像的多尺度特征。由相同大小的卷积核捕获的所有特征图直接输入到多尺度混合组（MHG）中；其次，每个MHG的卷积层由扩张卷积和标准卷积组成。混合卷积可以充分训练从先前和当前尺度卷积层获得的特征细节；三、每个混合卷积层的输出通过skip-connections送入后续的混合卷积层，从而产生密集连接；最后，使用meta-upscale模块作为upscale模块，可以将训练好的特征图放大任意比例因子。通过对各种图像进行评估，所提出的 MSN 网络在数值结果和视觉质量方面均优于最先进的方法。它可以放大训练后的特征图任意比例因子。通过对各种图像进行评估，所提出的 MSN 网络在数值结果和视觉质量方面均优于最先进的方法。它可以放大训练后的特征图任意比例因子。通过对各种图像进行评估，所提出的 MSN 网络在数值结果和视觉质量方面均优于最先进的方法。