Revealing Directions for Text-Guided 3D Face Editing
- 24 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 7961-7973
Abstract
3D face editing is a significant task in multimedia, aimed at the manipulation of 3D face models across various control signals. The success of 3D-aware GAN provides expressive 3D models learned from 2D single-view images only, encouraging researchers to discover semantic editing directions in its latent space. However, previous methods face challenges in balancing quality, efficiency, and generalization. To solve the problem, we explore the possibility of introducing the strength of diffusion model into 3D-aware GANs. In this paper, we present Face Clan, a fast and text-general approach for generating and manipulating 3D faces based on arbitrary attribute descriptions. To achieve disentangled editing, we propose to diffuse on the latent space under a pair of opposite prompts to estimate the mask indicating the region of interest on latent codes. Based on the mask, we then apply denoising to the masked latent codes to reveal the editing direction. Our method offers a precisely controllable manipulation method, allowing users to intuitively customize regions of interest with the text description. Experiments demonstrate the effectiveness and generalization of our Face Clan for various pre-trained GANs. It offers an intuitive and wide application for text-guided face editing that contributes to the landscape of multimedia content creation. Our project page: https://windlikestone.github.io/Face_clan_website/.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62571314, 62201342)
- CCF-NetEase ThunderFire Innovation Research Funding
- Shanghai Municipal Science and Technology Major Project (2021SHZDZX0102)
This publication has 68 references indexed in Scilit:
- Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images2024
- GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation2022
- GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields2021
- Closed-Form Factorization of Latent Semantics in GANs2021
- pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis2021
- Analyzing and Improving the Image Quality of StyleGAN2020
- StyleRig: Rigging StyleGAN for 3D Control Over Portrait Images2020
- ManiGAN: Text-Guided Image Manipulation2020
- StarGAN v2: Diverse Image Synthesis for Multiple Domains2020
- A Style-Based Generator Architecture for Generative Adversarial Networks2019