Autoencoders have become a hot researched topic in unsupervised learning due to their
ability to learn data features and act as a dimensionality reduction method. With rapid …

In the field of face/head-related product design, 3D statistical models (3DSMs) of human
heads and faces are widely used to model geometric variations, generate representative …

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 …

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 …

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 …

We present a multi-person soft-tissue avatar model. This model maps a body shape
descriptor to heterogeneous geometric and mechanical parameters of a soft-tissue model …

Unlike 2D face images, obtaining a 3D face is not easy. Existing methods, therefore, create a
3D face from a 2D face image (3D face reconstruction). A user might wish to edit the …

The automated generation of 3D human heads has been an intriguing and challenging task
for computer vision researchers. Prevailing methods synthesize realistic avatars but with …

Textures are a vital aspect of creating visually appealing and realistic 3D models. In this
paper, we study the problem of generating high-fidelity texture given shapes of 3D assets …

Learning 3D mesh representation is necessary for many computer vision and graphic tasks.
Recently, some works have studied convolution methods for directly processing input …