标题：Multi-scale generative adversarial network for image super-resolution

作者：Jiang Daihong, Zhang Sai, Dai Lei & Dai Yueming

网址:https://link.springer.com/article/10.1007/s00500-022-06822-5#citeas

求助者：欧朋

• 求助时间：2022/3/25 9:18:27
• 求助状态：AB图书馆客服已找到全文，详情咨询在线客服qq 1257749646
• 文献摘要：

In recent years, deep convolutional neural networks (CNNs) have been widely employed in image super-resolution. Thanks to the power of deep CNNs, the reconstruction performance is largely improved. However, the high-frequency information and details in the low-resolution image still can hardly be reconstructed. To deal with the above problems, we propose a multi-scale generative adversarial network in this paper. The multi-scale Pyramid module inside the generator could extract the features containing high-frequency information, and then the high-resolution image with the results of the bicubic interpolations is reconstructed. The discriminator in our model is used to identify the authenticity of the input image after refactoring. Our final loss function includes an adversarial loss and the mean square error (L2) reconstruction loss. In order to further improve the efficiency of training, the generator is pre-trained with the L2 loss, so as to improve the efficiency of the discriminator optimization. Compared with the algorithms based solely on normal plain convolutional networks, the proposed algorithm performs better in two indexes PSNR and SSIM of the super-resolution task.

文献《Multi-scale generative adversarial network for image super-resolution》已经找到全文，详情请咨询在线客服 qq 1257749646。
如果您还有其他需要寻找全文的文献，请点击文献求助提交

说明：文献求助是指AB图书馆根据读者的需求，为读者查找论文资料的服务。如果您搜索到相关资料，但不能获取全文，此时便可将有关信息提交求助，由值班客服为您寻找所需文献的全文。提供的文献均来自网络共享资源，不涉及版权交易；如侵犯了您的权利，请告知在线客服，立马删除。文件格式以PDF格式为主。