| 摘要: |
| 设计了新的生成器网络、判决器网络以及新的损失函数，用于图像场景转换.首先，生成器网络采用了带跨层连接结构的深度卷积神经网络，其中，多个跨层连接以实现图像结构信息的共享；而判决器网络采用了多尺度全域卷积网络，多尺度判决器可以区分不同尺寸下的真实和生成图像.同时，对于损失函数，该算法借鉴其他算法提出了4种损失函数的组合，并通过实验对比证明了新损失函数的有效性，包括GAN损失、L1损失、VGG损失、FM损失.从实验结果显示，该算法能够实现多种转换，且转换后图像的细节保留较为完整，生成图像较为真实，明显消除了块效应. |
| 关键词: 图像生成 深度学习 生成对抗网络 跨层连接 场景转换 |
| DOI：10.13328/j.cnki.jos.005986 |
| 分类号:TP183 |
| 基金项目:国家重点研发计划（2017YFB1302401）；国家自然科学基金（61471272） |
|
| Improved Generative Adversarial Network for Image Scene Transformation |
|
XIAO Jin-Sheng1, ZHOU Jing-Long1, LEI Jun-Feng1, LI Liang1, DING Ling2, DU Zhi-Yi1
|
|
1.Electronic Information School, Wuhan University, Wuhan 430072, China;2.College of Computer, Hubei University of Education, Wuhan 430205, China
|
| Abstract: |
| This study designs a new generator network, a new discriminator network, and a new loss function for image scene conversion. First, the generator network uses a deep convolutional neural network with a skip connection structure, in which multi-skip connection is used to share the structure information of the image. For the discriminator network, it uses a multi-scale global convolutional network which can distinguish between real and generated images of different sizes. At the same time, the new loss function is a combination of four loss functions referring to other algorithms, including GAN loss, L1 loss, VGG loss, and feature matching loss. Moreover, the validity of the new loss function is demonstrated through experimental comparisons. The experimental results show that the proposed algorithm can achieve multi-image transformations, and the details of generated images are preserved completely, the generated image is more realistic, and the block effect is obviously eliminated. |
| Key words: image generation deep learning generative adversarial networks skip connection scene conversion |
