ID |
原文 |
译文 |
40636 |
经测试验证,该设计方案有效可行,在满足功能需求的基础上能够保证可靠性和安全性. |
The test results show that the design scheme is effective and feasible, and can ensure the reliability and safety on the basis of meeting the functional requirements. |
40637 |
针对传统CycleGAN在图像去雾后出现模糊和颜色失真等问题,给出了一种改进CycleGAN的图像去雾网络. |
In view of the blur and color distortion in traditional CycleGAN image dehazing, animproved CycleGANImage dehazing network is proposed. |
40638 |
所提CycleGAN的生成器包括特征提取、特征融合和图像复原三个子网络. |
The generator of present CycleGAN consists three parts: feature extraction sub-network, feature fusion sub-network and image restoration sub-network. |
40639 |
图像特征提取子网络用于提取图像的内容特征和风格特征, |
The image feature extraction sub network is used to extract the content features and style features of the image. |
40640 |
特征融合子网络利用两种不同的注意力机制分别对提取到的内容特征和风格特征进行融合, |
The feature fusion sub network uses two different attention mechanisms to fuse the extracted content features and style features. |
40641 |
图像复原子网络将融合后的图像特征还原成无雾图像. |
The image complex atom network restores the fused image features to a haze free image. |
40642 |
与传统的CycleGAN和已有的去雾网络相比,所提网络对合成图像和真实图像均可取得理想的去雾结果,有效解决了传统CycleGAN在图像去雾后出现的模糊和颜色失真的问题. |
Compared with traditional CycleGAN and existing defogging networks, the proposed network can achieve ideal dehazing results for both synthetic images and real images, and effectively solves the problems of blurring and color distortion in traditional CycleGAN images after dehazing. |
40643 |
优化了简单生成对抗网络结构,用于更有效的通过对抗性实例训练得到视觉显着性图,减少假阳性产生和提高显著性. |
The structure of simple generated countermeasure network is optimized, whichis used to obtain visual saliency map more effectively through antagonistic case training, so as to reduce false positive and improve saliency. |
40644 |
网络模型仍遵循传统生成对抗网络结构, |
The network model still follows the traditional generation countermeasure network structure. |
40645 |
第一阶段是由一个使用残差结构建的生成器组成, |
In the first stage, it is composed of a generator built with residual structure. |