High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4569-4577
DOI: 10.1609/aaai.v38i5.28256 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Minghan Qin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).
Abstract (Originalsprache)
One crucial aspect of 3D head avatar reconstruction lies in the details of facial expressions. Although recent NeRF-based photo-realistic 3D head avatar methods achieve high-quality avatar rendering, they still encounter challenges retaining intricate facial expression details because they overlook the potential of specific expression variations at different spatial positions when conditioning the radiance field. Motivated by this observation, we introduce a novel Spatially-Varying Expression (SVE) conditioning. The SVE can be obtained by a simple MLP-based generation network, encompassing both spatial positional features and global expression information. Benefiting from rich and diverse information of the SVE at different positions, the proposed SVE-conditioned NeRF can deal with intricate facial expressions and achieve realistic rendering and geometry details of high-fidelity 3D head avatars. Additionally, to further elevate the geometric and rendering quality, we introduce a new coarse-to-fine training strategy, including a geometry initialization strategy at the coarse stage and an adaptive importance sampling strategy at the fine stage. Extensive experiments indicate that our method outperforms other state-of-the-art (SOTA) methods in rendering and geometry quality on mobile phone-collected and public datasets. Code and data can be found at https://github.com/minghanqin/AvatarSVE.
Zitieren
APA
Qin, M., Liu, Y., Xu, Y., Zhao, X., Liu, Y., & Wang, H. (2024). High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4569-4577. https://doi.org/10.1609/aaai.v38i5.28256
Vancouver
Qin M, Liu Y, Xu Y, Zhao X, Liu Y, Wang H. High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4569-4577. doi:10.1609/aaai.v38i5.28256
BibTeX
@article{Qin2024,
author = {Qin, Minghan and Liu, Yifan and Xu, Yuelang and Zhao, Xiaochen and Liu, Yebin and Wang, Haoqian},
title = {High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {5},
pages = {4569--4577},
doi = {10.1609/aaai.v38i5.28256}
}
EUVIMED