2023年第1期目次

超分辨率(SR)是一类重要的数字图像处理技术，其根据一个观测者得到的低分辨率(LR)图像重 建并输出一个相应的高分辨率(HR)图像，从而提高现代数字图像的分辨率。SR 在数字图像压缩与传输、医学 成像、遥感成像、视频感知与监控等学科中的研究与应用价值巨大。随着深度学习的快速发展，结合最新的深 度学习方法，可以为 SR 问题提供创新性的解决方案。首先回顾 SR 的背景意义、发展过程以及将深度学习应 用于 SR 的技术价值。其次简要介绍传统 SR 算法的基本方法、分类和优缺点；按照不同的实现技术和网络类 型对基于深度学习的 SR 方法进行了分类介绍，重点分析对比了卷积神经网络(CNN)、残差网络(ResNet)和生成 对抗网络(GAN)在 SR 中的应用。然后介绍主要评价指标和解决策略，并对不同的 SR 算法在标准数据集中的 性能表现进行对比。最后总结基于深度学习的 SR 算法，并对未来发展趋势进行展望。

Review of image super-resolutionbased on deep learning

Super-resolution (SR) is an essential technology in digital image processing that reconstructs and produces a matching high-resolution (HR) image based on the low-resolution (LR) image obtained by an observer, thereby improving the resolution of modern digital images. This technology is of significant research and practical value in fields such as digital image compression and transmission, medical imaging, remote sensing imaging, and video perception and monitoring. With the rapid growth of deep learning, novel solutions for SR challenges can be obtained by combining the latest deep learning algorithms. First, discussions were made on the background, development, and technological value of applying deep learning to SR. Second, a brief overview was provided concerning the fundamental methodology, categorization, and advantages and disadvantages of the classic SR methods. Deep learning-based SR methods were categorized and introduced based on distinct implementation strategies and network types. The application of convolutional neural networks (CNN), residual networks (ResNet), and generative adversarial networks (GAN) in SR was investigated and contrasted. The major evaluation indices and solution methodologies were then presented, and the performance of several SR methods on typical data sets was compared. Finally, the deep learning-based SR method was summarized, and the future development trend was forecasted.