Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction
Guy Gafni1 Justus Thies1 Michael Zollhöfer2 Matthias Nießner1
1Technical University of Munich 2Facebook Reality Labs
Introduction
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 viewpoint 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.
Video
Video
Publication
Paper - ArXiv - pdf (abs) | GitHubIf you find our work useful, please consider citing it:
@InProceedings{Gafni_2021_CVPR,
author = {Gafni, Guy and Thies, Justus and Zollh{\"o}fer, Michael and Nie{\ss}ner, Matthias},
title = {Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021},
pages = {8649-8658}
}