FFaceNeRF：神经辐射场中的少样本人脸编辑

FFaceNeRF: Few-shot Face Editing in Neural Radiance Fields

March 21, 2025

作者: Kwan Yun, Chaelin Kim, Hangyeul Shin, Junyong Noh

cs.AI

摘要

近期，利用掩码进行3D人脸编辑的方法通过借助神经辐射场（NeRF）技术，已能生成高质量的编辑图像。尽管这些方法表现卓越，但由于依赖预训练的分割掩码，现有方法往往在用户控制方面受限。为了使用符合特定布局的掩码，需要大量训练数据，而收集此类数据颇具挑战。我们提出了FFaceNeRF，一种基于NeRF的人脸编辑技术，旨在克服因固定掩码布局带来的用户控制局限。该方法采用配备特征注入的几何适配器，有效操控几何属性。此外，我们引入了潜在混合技术以增强三平面表示，使得仅需少量样本即可完成训练。这加速了模型对期望掩码布局的适应，对于个性化医疗成像或创意人脸编辑等应用至关重要。对比评估显示，FFaceNeRF在灵活性、控制力及生成图像质量上均优于现有的基于掩码的人脸编辑方法，为未来定制化与高保真3D人脸编辑的发展铺平了道路。代码已发布于{https://kwanyun.github.io/FFaceNeRF_page/{项目页面}}。

English

Recent 3D face editing methods using masks have produced high-quality edited images by leveraging Neural Radiance Fields (NeRF). Despite their impressive performance, existing methods often provide limited user control due to the use of pre-trained segmentation masks. To utilize masks with a desired layout, an extensive training dataset is required, which is challenging to gather. We present FFaceNeRF, a NeRF-based face editing technique that can overcome the challenge of limited user control due to the use of fixed mask layouts. Our method employs a geometry adapter with feature injection, allowing for effective manipulation of geometry attributes. Additionally, we adopt latent mixing for tri-plane augmentation, which enables training with a few samples. This facilitates rapid model adaptation to desired mask layouts, crucial for applications in fields like personalized medical imaging or creative face editing. Our comparative evaluations demonstrate that FFaceNeRF surpasses existing mask based face editing methods in terms of flexibility, control, and generated image quality, paving the way for future advancements in customized and high-fidelity 3D face editing. The code is available on the {https://kwanyun.github.io/FFaceNeRF_page/{project-page}}.