Designing realistic digital humans is extremely complex. Most data-driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape attributes. In this paper, we overcome this limitation by introducing a novel loss function grounded in spectral geometry and applicable to different neural-network-based generative models of 3D head and body meshes. Encouraging the latent variables of mesh variational autoencoders (VAEs) or generative adversarial networks (GANs) to follow the local eigenprojections of identity attributes, we improve latent disentanglement and properly decouple the attribute creation. Experimental results show that our local eigenprojection disentangled (LED) models not only offer improved disentanglement with respect to the state-of-the-art, but also maintain good generation capabilities with training times comparable to the vanilla implementations of the models.

翻译：设计逼真的数字人类极其复杂。大多数用于简化其底层几何形状生成的数据驱动生成模型，无法控制局部形状属性的生成。本文通过引入一种基于谱几何的新型损失函数克服了这一局限，该函数适用于基于神经网络的三维头部及身体网格生成模型。通过鼓励网格变分自编码器或生成对抗网络的潜在变量遵循身份属性的局部特征投影，我们改善了潜在解耦效果，并有效分离了属性的生成过程。实验结果表明，我们的局部特征投影解耦模型不仅相较现有技术实现了更优的解耦性能，还能在保持与基础模型相当训练时间的同时，维持良好的生成能力。