Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction

TL;DR

This paper introduces a novel dynamic neural radiance field approach for reconstructing and rendering 4D facial avatars from monocular videos, enabling realistic and controllable face modeling for AR/VR applications.

Contribution

It combines implicit neural scene representations with a morphable model to handle facial dynamics, learned solely from monocular data, surpassing existing methods in realism.

Findings

Achieves photo-realistic facial image generation.

Outperforms state-of-the-art video reenactment methods.

Operates without specialized capture setups.

Abstract

We present dynamic neural radiance fields for modeling the appearance and dynamics of a human face. Digitally modeling and reconstructing a talking human is a key building-block for a variety of applications. Especially, for telepresence applications in AR or VR, a faithful reproduction of the appearance including novel viewpoints or head-poses is required. In contrast to state-of-the-art approaches that model the geometry and material properties explicitly, or are purely image-based, we introduce an implicit representation of the head based on scene representation networks. To handle the dynamics of the face, we combine our scene representation network with a low-dimensional morphable model which provides explicit control over pose and expressions. We use volumetric rendering to generate images from this hybrid representation and demonstrate that such a dynamic neural scene representation can be learned from monocular input data only, without the need of a specialized capture setup. In our experiments, we show that this learned volumetric representation allows for photo-realistic image generation that surpasses the quality of state-of-the-art video-based reenactment methods.