StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

TL;DR

StyleMM is a new framework that creates stylized 3D face models from text descriptions by leveraging text-guided image translation and attribute preservation, enabling consistent and diverse stylized 3D faces.

Contribution

It introduces a method to generate stylized 3D morphable face models from text prompts using a novel stylization approach that preserves facial attributes during image translation.

Findings

Outperforms state-of-the-art in identity preservation and stylization.

Enables explicit control over shape, expression, and texture.

Produces consistent, animatable 3D face meshes.

Abstract

We introduce StyleMM, a novel framework that can construct a stylized 3D Morphable Model (3DMM) based on user-defined text descriptions specifying a target style. Building upon a pre-trained mesh deformation network and a texture generator for original 3DMM-based realistic human faces, our approach fine-tunes these models using stylized facial images generated via text-guided image-to-image (i2i) translation with a diffusion model, which serve as stylization targets for the rendered mesh. To prevent undesired changes in identity, facial alignment, or expressions during i2i translation, we introduce a stylization method that explicitly preserves the facial attributes of the source image. By maintaining these critical attributes during image stylization, the proposed approach ensures consistent 3D style transfer across the 3DMM parameter space through image-based training. Once trained, StyleMM enables feed-forward generation of stylized face meshes with explicit control over shape, expression, and texture parameters, producing meshes with consistent vertex connectivity and animatability. Quantitative and qualitative evaluations demonstrate that our approach outperforms state-of-the-art methods in terms of identity-level facial diversity and stylization capability. The code and videos are available at [kwanyun.github.io/stylemm_page](kwanyun.github.io/stylemm_page).