Zhang Xu, Wu Jinxin
Software Engineering Institute, Xiamen University of Technology, Xiamen, 361000, China.
Sci Rep. 2024 Sep 4;14(1):20636. doi: 10.1038/s41598-024-69674-z.
With the 5G and the popularity of high-definition and ultrahigh-definition equipment, people have increasingly higher requirements for the resolution of images or videos. However, the transmission pressure on servers is also gradually increasing. Therefore, superresolution technology has attracted much attention in recent years. Simultaneously, with the further development of deep learning techniques, superresolution research is shifting from the calculation of traditional algorithms to the deep learning method, which exhibits a greatly superior final display. First, the traditional block-matching-3D (BM3D) algorithm is formed as the postprocessing module, which can avoid the uneven edge of GAN network recovery, make the picture appear more authentic, and improve the viewer's subjective feelings. Next, the adaptive-downsampling model (ADM) is utilized to train models for specific camera styles. The high-resolution (HR) data sequence is subsequently downsampled to a low-resolution (LR) data sequence, enabling the superresolution algorithm to utilize this training set. This method can obtain better results and improve overall performance by 0.1~0.3 dB.
随着5G以及高清和超高清设备的普及，人们对图像或视频的分辨率要求越来越高。然而，服务器上的传输压力也在逐渐增加。因此，超分辨率技术近年来备受关注。同时，随着深度学习技术的进一步发展，超分辨率研究正从传统算法的计算转向深度学习方法，深度学习方法在最终显示上表现出极大的优势。首先，将传统的三维块匹配（BM3D）算法构建为后处理模块，它可以避免GAN网络恢复时边缘不均匀的问题，使图片看起来更真实，并提升观看者的主观感受。接下来，利用自适应下采样模型（ADM）针对特定相机样式训练模型。随后将高分辨率（HR）数据序列下采样为低分辨率（LR）数据序列，以使超分辨率算法能够利用此训练集。该方法可以获得更好的结果，并将整体性能提高0.1~0.3 dB。
