Facial Image Manipulation via Discriminative Decomposition of Semantic Space
Facial Image Manipulation via Discriminative Decomposition of Semantic Space
复制标题
DOI：
10.1109/ijcnn54540.2023.10191767
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Jiazhou Zheng;Hiroaki Aizawa;Takio Kurita
中科院分区：
文献类型：
--
作者：
Jiazhou Zheng;Hiroaki Aizawa;Takio Kurita
生成对抗网络（GAN）可以学习高度信息化的潜在空间。通过操纵潜在空间中的潜在表示，我们可以控制生成图像中的属性，而无需修改GAN本身的模型。现有的研究大多在潜空间中找到每个语义的方向向量，并使用线性计算来控制图像中的语义变化。然而，逆语义方向移动仍然使潜在表征受制于潜在空间中属性的纠缠。为此，针对潜在空间中属性纠缠的问题，提出了一种分解方法，将预先训练好的潜在空间分解为身份信息子空间和属性信息子空间，通过在属性信息子空间中移动实现潜在表示的语义变化。在我们的实验中，我们评估了它的有效性，并比较了属性改变后的图像。实验表明，该方法能进一步解决隐空间中的属性纠缠问题，有效降低属性改变后对隐表示中其他内容的影响。
Generative Adversarial Networks (GANs) can learn a highly informative latent space. By manipulating the latent representation in the latent space, we can control attributes in the generated images without modifying the model of GAN itself. Most existing studies find the direction vector of each semantic in the latent space and steer the latent vectors using linear computation to control semantic changes in the images. However, moving against the semantic direction still makes the latent representation subject to the entanglement of attributes in the latent space. Therefore, to solve the problem of attribute entanglement in latent space, we propose a decomposition method that decomposes the identity information subspace and the attribute information subspace from the pre-trained latent space and realize the semantic change of the latent representation by moving in the attribute information subspace. In our experiments, we evaluated its effectiveness and compared the images after the attribute change. The experiments demonstrated that our method can further solve the attribute entanglement problem in the latent space and effectively reduce the impact on other contents in the latent representation after changing the attributes.