arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.13028eess.IVcs.CV
收藏

基于多尺度特征交互网络的轻量级图像超分辨率

Lightweight Image Super-Resolution with Multi-scale Feature Interaction Network

Nanjing University of Posts and Telecommunications(南京邮电大学);East China Normal University(华东师范大学);National Institute of Informatics(国立情报学研究所);Kyushu Institute of Technology(九州工业大学)

Zhengxue Wang, Guangwei Gao, Juncheng Li, Yi Yu, Huimin Lu

摘要:

最近,具有深度和复杂卷积神经网络结构的单图像超分辨率(SISR)方法已经取得了令人满意的性能。然而,这些方法提高了性能的代价是更高的内存消耗,这是很难适用于一些移动设备与有限的存储和计算资源。为了解决这个问题,我们提出了一个轻量级的多尺度特征交互网络(MSFIN)。对于轻量级SISR,MSFIN扩展了接收场,并充分利用了各种尺度和交互式连接的低分辨率观测图像的信息特征。此外,我们设计了一个轻量级的经常性的残留信道注意块(RRCAB),使网络可以受益于信道注意机制,同时足够轻量级。在一些基准上进行的大量实验已经证实,我们提出的MSFIN可以通过更轻量级的模型实现与最先进的MSFIN相当的性能。

英文摘要:

Recently, the single image super-resolution (SISR) approaches with deep and complex convolutional neural network structures have achieved promising performance. However, those methods improve the performance at the cost of higher memory consumption, which is difficult to be applied for some mobile devices with limited storage and computing resources. To solve this problem, we present a lightweight multi-scale feature interaction network (MSFIN). For lightweight SISR, MSFIN expands the receptive field and adequately exploits the informative features of the low-resolution observed images from various scales and interactive connections. In addition, we design a lightweight recurrent residual channel attention block (RRCAB) so that the network can benefit from the channel attention mechanism while being sufficiently lightweight. Extensive experiments on some benchmarks have confirmed that our proposed MSFIN can achieve comparable performance against the state-of-the-arts with a more lightweight model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑