MoFaNeRF: Morphable Facial Neural Radiance Field

TL;DR

MoFaNeRF is a neural radiance field-based parametric model that enables photo-realistic facial synthesis, editing, and view synthesis by encoding facial shape, expression, and appearance, surpassing traditional 3DMM capabilities.

Contribution

This work introduces the first neural radiance field-based facial parametric model, MoFaNeRF, capable of high-fidelity synthesis, editing, and manipulation of facial images.

Findings

Outperforms traditional 3DMM in realism and detail.

Enables smooth face morphing through code interpolation.

Achieves competitive results in face fitting, generation, and editing tasks.

Abstract

We propose a parametric model that maps free-view images into a vector space of coded facial shape, expression and appearance with a neural radiance field, namely Morphable Facial NeRF. Specifically, MoFaNeRF takes the coded facial shape, expression and appearance along with space coordinate and view direction as input to an MLP, and outputs the radiance of the space point for photo-realistic image synthesis. Compared with conventional 3D morphable models (3DMM), MoFaNeRF shows superiority in directly synthesizing photo-realistic facial details even for eyes, mouths, and beards. Also, continuous face morphing can be easily achieved by interpolating the input shape, expression and appearance codes. By introducing identity-specific modulation and texture encoder, our model synthesizes accurate photometric details and shows strong representation ability. Our model shows strong ability on multiple applications including image-based fitting, random generation, face rigging, face editing, and novel view synthesis. Experiments show that our method achieves higher representation ability than previous parametric models, and achieves competitive performance in several applications. To the best of our knowledge, our work is the first facial parametric model built upon a neural radiance field that can be used in fitting, generation and manipulation. The code and data is available at https://github.com/zhuhao-nju/mofanerf.