唐家福,穆平安.基于多尺度稠密卷积网络的单图像超分辨率重建[J].包装工程,2020,41(13):267-273.
TANG Jia-fu,MU Ping-an.Single Image Super-resolution Reconstruction Based on Multiscale DenseNet[J].Packaging Engineering,2020,41(13):267-273. |
| 基于多尺度稠密卷积网络的单图像超分辨率重建 |
| Single Image Super-resolution Reconstruction Based on Multiscale DenseNet |
| 投稿时间：2019-11-05 修订日期：2020-07-10 |
| DOI：10.19554/j.cnki.1001-3563.2020.13.038 |
| 中文关键词: 图像超分辨 卷积神经网络 多尺度信息 稠密连接 |
| 英文关键词: image super-resolution convolutional neural network multiscale information dense connection |
| 基金项目: |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 目的 针对已有网络对于卷积特征图利用率低下，从而导致高倍数图像重建质量不高的情况，提出一种多尺度稠密卷积网络（SRMD）。方法 对SRDenseNet的稠密连接模块进行改进，去除批规范化层，参考已有网络，设计多尺度特征提取层和1×1的信息整合层，从而构成多尺度稠密卷积模块。SRMD通过一个多尺度特征提取层堆叠64个底层特征图，再由8个多尺度稠密卷积模块经过稠密连接堆叠1024个特征图，最后通过信息整合和子像素卷积模块输出超分辨率重建图像。结果 在Set5，Set14，B100和U100数据集上进行测试，SRMD重建图像的峰值信噪比分别为30.1570，26.9952，25.7860, 23.4821 dB，结构相似性分别为0.8813，0.7758，0.7243, 0.7452。结论 与已有网络相比，SRMD与DRCN，VDSR表现相当，优于SRDenseNet和BiCubic方法。 |
| 英文摘要: |
| This paper aims to propose a multi-scale dense convolution network (SRMD) to solve the problem of low utilization of convolution feature map and low reconstruction quality of high-power image. In this paper, the dense connection module of SRDenseNet was improved, and the batch normalization layer was removed. Referring to the existing network, the information integration layer of multi-scale feature extraction layer and 1×1 was designed to form a multi-scale dense convolution module. SRMD stacked 64 low-level feature images through a multi-scale feature extraction layer, and then stacked 1024 feature images through 8 multi-scale dense convolution modules after dense connection. Finally, SRMD output super-resolution reconstruction images through information integration and sub-pixel convolution modules. In this paper, the test is carried out on Set5, Set14, B100 and U100. The peak signal-to-noise ratio of SRMD reconstructed image is 30.1570, 26.9952, 25.7860 and 23.4821 dB, respectively, and the structural similarity is 0.8813, 0.7758, 0.7243 and 0.7452. Compared with the existing networks, SRMD, DRCN and VDSR have the same performance, superior to SRDenseNet and BiCubic methods. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
渝公网安备 50010702501716号