filename     : Ott25a.pdf
entry        : inproceedings
conference   : Shape Modeling International 2025, Hangzhou, China, 29th October - 2nd November, 2025
pages        : 104325
year         : 2025
month        : October
title        : Multimodal Conditional 3D Face Geometry Generation
subtitle     :
author       : Christopher Otto, Prashanth Chandran, Sebastian Weiss, Markus Gross, Gaspard Zoss, Derek Bradley
booktitle    : Computers & Graphics
ISSN/ISBN    : 0097-8493
editor       : 
publisher    : Elsevier
publ.place   : 
volume       : 132
issue        :
language     : English
keywords     : Multimodal generation, 3D face geometry, Deep learning
abstract     : We present a new method for multimodal conditional 3D face geometry generation that allows user-friendly control over the output identity and expression via a number of different conditioning signals. Within a single model, we demonstrate 3D faces generated from artistic sketches, portrait photos, Canny edges, FLAME face model parameters, 2D face landmarks, or text prompts. Our approach is based on a diffusion process that generates 3D geometry in a 2D parameterized UV domain. Geometry generation passes each conditioning signal through a set of cross-attention layers (IP-Adapter), one set for each user-defined conditioning signal. The result is an easy-to-use 3D face generation tool that produces topology-consistent, high-quality geometry with fine-grain user control.