FENeRF: Face Editing in Neural Radiance Fields

by   Jingxiang Sun, et al.

Previous portrait image generation methods roughly fall into two categories: 2D GANs and 3D-aware GANs. 2D GANs can generate high fidelity portraits but with low view consistency. 3D-aware GAN methods can maintain view consistency but their generated images are not locally editable. To overcome these limitations, we propose FENeRF, a 3D-aware generator that can produce view-consistent and locally-editable portrait images. Our method uses two decoupled latent codes to generate corresponding facial semantics and texture in a spatial aligned 3D volume with shared geometry. Benefiting from such underlying 3D representation, FENeRF can jointly render the boundary-aligned image and semantic mask and use the semantic mask to edit the 3D volume via GAN inversion. We further show such 3D representation can be learned from widely available monocular image and semantic mask pairs. Moreover, we reveal that joint learning semantics and texture helps to generate finer geometry. Our experiments demonstrate that FENeRF outperforms state-of-the-art methods in various face editing tasks.


page 1

page 4

page 5

page 6

page 7

page 8


Designing a 3D-Aware StyleNeRF Encoder for Face Editing

GAN inversion has been exploited in many face manipulation tasks, but 2D...

IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aware Portrait Synthesis

Existing 3D-aware facial generation methods face a dilemma in quality ve...

Fine-Grained Face Swapping via Regional GAN Inversion

We present a novel paradigm for high-fidelity face swapping that faithfu...

NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fields

Recent methods for synthesizing 3D-aware face images have achieved rapid...

Geometry-Aware Face Completion and Editing

Face completion is a challenging generation task because it requires gen...

3DAvatarGAN: Bridging Domains for Personalized Editable Avatars

Modern 3D-GANs synthesize geometry and texture by training on large-scal...

Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field

Recently 3D-aware GAN methods with neural radiance field have developed ...

Please sign up or login with your details

Forgot password? Click here to reset