人工智能
计算机科学
平滑的
图像(数学)
生成语法
特征(语言学)
纹理(宇宙学)
图像纹理
模式识别(心理学)
生成对抗网络
对抗制
计算机视觉
图像融合
噪音(视频)
图像复原
人工神经网络
图像处理
GSM演进的增强数据速率
迭代重建
融合
纹理过滤
特征提取
像素
特征检测(计算机视觉)
计算复杂性理论
传感器融合
深度学习
特征学习
作者
Jingsheng Lei,Hanbo Xue,Shengying Yang,Wenbin Shi,Shuping Zhang,Yi Wu
标识
DOI:10.1117/1.jei.31.3.033011
摘要
At present, generative adversarial network (GAN) has made outstanding progress for image super-resolution (SR), solving the problem of edge smoothing in SR images. Nevertheless, there are also problems with a lack of texture details, noise, and artifacts. The high-frequency (HF) information of an image is significant for keeping the texture part of the reconstructed image, and the introduction of HF information can increase the learning ability of super-resolution generative adversarial network (SRGAN) for the image features, so we propose a super-resolution GAN based on high-frequency feature fusion (HFF-SRGAN), which can increase the texture detail of the reconstructed image and reduce the noise and artifacts with less computational cost. Experimental results show that our algorithm evaluates significantly better than SRGAN and has significant advantages in texture details and noise compared with other SR algorithms.
科研通智能强力驱动
Strongly Powered by AbleSci AI