Zang Huaijuan, Cheng Guoan, Duan Zhipeng, Zhao Ying, Zhan Shu
Key Laboratory of Knowledge Engineering with Big Data, Ministry of Education, School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, China.
Entropy (Basel). 2022 Mar 31;24(4):489. doi: 10.3390/e24040489.
The development of display technology has continuously increased the requirements for image resolution. However, the imaging systems of many cameras are limited by their physical conditions, and the image resolution is often restrictive. Recently, several models based on deep convolutional neural network (CNN) have gained significant performance for image super-resolution (SR), while extensive memory consumption and computation overhead hinder practical applications. For this purpose, we present a lightweight network that automatically searches dense connection (ASDCN) for image super-resolution (SR), which effectively reduces redundancy in dense connection and focuses on more valuable features. We employ neural architecture search (NAS) to model the searching of dense connections. Qualitative and quantitative experiments on five public datasets show that our derived model achieves superior performance over the state-of-the-art models.
显示技术的发展不断提高了对图像分辨率的要求。然而，许多相机的成像系统受到其物理条件的限制，图像分辨率往往具有局限性。最近，几种基于深度卷积神经网络（CNN）的模型在图像超分辨率（SR）方面取得了显著性能，但大量的内存消耗和计算开销阻碍了实际应用。为此，我们提出了一种用于图像超分辨率（SR）的自动搜索密集连接的轻量级网络（ASDCN），它有效地减少了密集连接中的冗余，并专注于更有价值的特征。我们采用神经架构搜索（NAS）对密集连接的搜索进行建模。在五个公共数据集上进行的定性和定量实验表明，我们推导的模型比现有最先进的模型具有更优的性能。
