NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fields
This addresses the need for more flexible and efficient 3D-aware face editing tools for applications in computer graphics and vision, though it is incremental as it builds on existing tri-plane-based neural radiance field methods.
The paper tackles the problem of independently editing facial geometry and appearance in neural radiance fields, which existing methods struggle with due to retraining requirements and lag behind generation processes. The result is NeRFFaceEditing, which enables decoupled control while maintaining high quality and fast inference, with both qualitative and quantitative evaluations showing superior performance compared to alternatives.
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 method compared to existing and alternative solutions.