规范化(社会学)
计算机科学
生成语法
人工智能
发电机(电路理论)
对抗制
生成对抗网络
计算机视觉
模式识别(心理学)
图像(数学)
人类学
量子力学
物理
社会学
功率(物理)
作者
Xinrong Hu,Qing Chang,Junjie Huang,Ruiqi Luo,Bangchao Wang,Heng Chang
标识
DOI:10.1007/s00371-023-02998-5
摘要
Hair synthesis plays a crucial role in generating facial images, but the complex textures and varied shapes of hair create obstacles in creating genuine images of hair on photographs utilizing generative adversarial networks. This research paper proposes an inventive normalization technique, HSSAN (Hair Style-Guided Spatially Adaptive Normalization), that incorporates four connected phases, each set exclusively for hair feature attributes, and uses them to improve the generator to generate hairstyle transfer images. The hair synthesizer generator utilizes several HSSAN residual blocks in the network framework, while the input modules comprise only an appearance module and a background module. Furthermore, a regularized loss function is introduced to regulate the style vector. Through the network, realistic hair generation images can be generated. We employed the FFHQ dataset to perform our experiments and observed that our methodology generates hair images surpassing existing generative adversarial network-based methods in terms of visual realism and Fréchet Inception Distance.
科研通智能强力驱动
Strongly Powered by AbleSci AI