TextHair3D: Text-driven 3D Hair Editing with Generative Priors
Xiaoxue Li, Huilong Pi, Yunchuan Qin, Ruihui Li, Kenli Li
Abstract
Text-driven hair editing on 3D heads is a challenging problem in computer vision and graphics. In this paper, we propose TextHair3D, a NeRF-based text-driven 3D hair editing method that uses 3D perception to generate priors, edit hair attributes from user-provided text, and preserve facial features. TextHair3D uses the Contrastive Language-Image Pre-training (CLIP) model to encode textual conditions. To address the complexity and roughness of local editing, we design a combined conditional mapping module to map image and text conditions into latent space for learning generative priors. This enables high-quality, photo-realistic hair editing and 3D head reproduction. Extensive experiments show Tex-tHair3D’s superiority in visual realism and attribute accuracy.
BibTeX
@inproceedings{icassp2025_texthair3dtextdr,
title = {TextHair3D: Text-driven 3D Hair Editing with Generative Priors},
author = {Xiaoxue Li and Huilong Pi and Yunchuan Qin and Ruihui Li and Kenli Li},
booktitle = {ICASSP 2025},
year = {2025}
}