We study how to optimize the latent space of neural shape generators that map latent codes
to 3D deformable shapes. The key focus is to look at a deformable shape generator from a …

In the realm of 3D computer vision, parametric models have emerged as a ground-breaking
methodology for the creation of realistic and expressive 3D avatars. Traditionally, they rely …

Abstract We present the Locally Adaptive Morphable Model (LAMM) a highly flexible Auto-
Encoder (AE) framework for learning to generate and manipulate 3D meshes. We train our …

Background and objective: The use of deep learning to undertake shape analysis of the
complexities of the human head holds great promise. However, there have traditionally been …

Deep generative models such as Variational Autoencoders (VAEs), Generative Adversarial
Networks (GANs), and diffusion models have demonstrated their efficacy in generating 2D …

针对三维人脸生成任务中不能精确地控制局部属性生成的问题, 提出球谐函数局部特征投影的
三维人脸生成方法. 首先将三维人脸划分为多个属性, 每个属性对应多个潜变量; …

Previous 3D face analysis has focussed on 3D facial identity, expression and pose
disentanglement. However, the independent control of different facial parts and the ability to …

Développer des modèles capables de comprendre la dynamique du corps humain
représente aujourd'hui un défi important dans le domaine de l'informatique graphique. Les …

To address the challenge of accurately controlling local features in the 3D face generation
task, a 3D face generation method with local feature projection of spherical harmonics is …