| 引用本文: | 刘超,张晓晖,胡清平.图像超分辨率卷积神经网络加速算法.[J].国防科技大学学报,2019,41(2):91-97.[点击复制] |
| LIU Chao,ZHANG Xiaohui,HU Qingping.Image super resolution convolution neural network acceleration algorithm[J].Journal of National University of Defense Technology,2019,41(2):91-97[点击复制] |
|
| |
|
|
| 本文已被：浏览 7168次 下载 5866次 |
| 图像超分辨率卷积神经网络加速算法 |
| 刘超1,2, 张晓晖1, 胡清平1 |
|
(1.海军工程大学 兵器工程学院, 湖北 武汉 430033;2.军事科学院 系统工程研究院, 北京 100044)
|
| 摘要: |
| 为了实现模型的实时和嵌入式运行，提出了一种轻量级的卷积神经网络结构。通过采用较小的滤波器尺寸和引入深度可分离卷积，可大量减少模型参数，提高模型非线性表达能力；在网络末端引入子像素卷积层，直接从原始低分辨率图像学习到高分辨率图像的映射，计算成本为原来的1/k2(k为放大因子)。在Set5数据集上的实验表明，所提模型的速度较经典的图像超分辨率重建算法速度提高了25.8倍，能够在通用GPU上实时运行，峰值信噪比平均提高了0.17 dB，并且参数只有它的35%。 |
| 关键词: 卷积神经网络 超分辨率重建 深度可分离卷积 子像素卷积 |
| DOI：10.11887/j.cn.201902014 |
| 投稿日期：2017-12-15 |
| 基金项目:国家部委基金资助项目（4010501050401） |
|
| Image super resolution convolution neural network acceleration algorithm |
| LIU Chao1,2, ZHANG Xiaohui1, HU Qingping1 |
|
(1.College of Weaponry Engineering, Naval University of Engineering, Wuhan 430033, China;2.System Engineering Research Institute, Academy of Military Science, Beijing 100044, China)
|
| Abstract: |
| In order to realize the real-time and embedded operation of the model, a lightweight convolution neural network structure was proposed. By using a smaller filter size and introducing depthwise separable convolution, a large number of model parameters can be subtracted and the nonlinear capability can be improved. The sub-pixel convolution was introduced at the end of the network, then the mapping was learned directly from the original low-resolution image (without interpolation) to the high-resolution one, the cost is 1/k2 as much as before (k is the magnification factor). Experimental results on Set5 show that the proposed model is more than 25.8 times faster than the classical super resolution reconstruction algorithm and can run in real-time on a common GPU; and the proposed method with only 35% parameters of SRCNN(super resolution convolution neural network), improves the PSNR(peak signal to noise ratio) with value of 0.17 dB. |
| Keywords: convolution neural network super-resolution reconstruction depthwise separable convolution sub-pixel convolution |
|
|
|
|
|
