Multimodal Conditional 3D Face Geometry Generation

Download PDF
Open Webpage

Christopher Otto, Prashanth Chandran, Sebastian Weiss, Markus Gross, Gaspard Zoss, Derek Bradley

Published: 01 Jan 2025, Last Modified: 04 Nov 2025Comput. Graph. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•We present a new method for 3D face geometry generation from 6 different types of conditionings (prompts) within a single model.•We propose a comprehensive solution for training such a method from scratch, with 3D geometry data augmentations and by representing 3D geometry as position maps to better fit existing diffusion pipelines.•We show that our method supports face generation with expressions, sketch-based editing for 3D face design, stochastic variations of details conditioned on low resolution FLAME faces, generalization to in-the-wild data and dynamic face generation from videos.