Multimodal Conditional 3D Face Geometry Generation
Christopher Otto, P. Chandran, S. Weiss, M. Gross, G. Zoss, D. Bradley
Shape Modeling International (Hangzhou, China, October 29 - November 2, 2025), Computers & Graphics, vol. 132, no. 104325, 2025, pp. 1-10
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.
