Towards High-Quality and Disentangled Face Editing in a 3D GAN

作者：Kaiwen Jiang, Shuyu Chen, Fenglin Liu, Hongbo Fu, Lin Gao · 发表于：IEEE Transactions on Pattern Analysis and Machine Intelligence · 年份：2025 · DOI：10.1109/tpami.2024.3523422 · 被引用次数：5 · 研究领域：Face recognition and analysis、Generative Adversarial Networks and Image Synthesis、Facial Nerve Paralysis Treatment and Research

Recent methods for synthesizing 3D-aware face images have achieved rapid development thanks to neural radiance fields, allowing for high quality and fast inference speed. However, existing solutions for editing facial geometry and appearance independently usually require retraining and are not optimized for the recent work of generation, thus tending to lag behind the generation process. To address these issues, we introduce NeRFFaceEditing, which enables editing and decoupling geometry and appearance in the pretrained tri-plane-based neural radiance field while retaining its high quality and fast inference speed. Our key idea for disentanglement is to use the statistics of the tri-plane to represent the high-level appearance of its corresponding facial volume. Moreover, we leverage a generated 3D-continuous semantic mask as an intermediary for geometry editing. We devise a geometry decoder (whose output is unchanged when the appearance changes) and an appearance decoder. The geometry decoder aligns the original facial volume with the semantic mask volume. We also enhance the disentanglement by explicitly regularizing rendered images with the same appearance but different geometry to be similar in terms of color distribution for each facial component separately. Our method allows users to edit via semantic masks with decoupled control of geometry and appearance. Both qualitative and quantitative evaluations show the superior geometry and appearance control abilities of our me...