Loc3Diff: Local Diffusion for 3D Human Head Synthesis and Editing
Abstract
We present a novel framework for generating photorealistic 3D human head and subsequently manipulating and reposing them with remarkable flexibility. The proposed approach constructs an implicit representation of 3D human heads, anchored on a parametric face model. To enhance representational capabilities and encode spatial information, we represent semantic consistent head region by a local tri-plane, modulated by a 3D Gaussian. Additionally, we parameterize these tri-planes in a 2D UV space via a 3DMM, enabling effective utilization of the diffusion model for 3D head avatar generation. Our method facilitates the creation of diverse and realistic 3D human heads with flexible global and fine-grained region-based editing over facial structures, appearance and expressions. Extensive experiments demonstrate the effectiveness of our method.
Cite
Text
Lan et al. "Loc3Diff: Local Diffusion for 3D Human Head Synthesis and Editing." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73650-6_4Markdown
[Lan et al. "Loc3Diff: Local Diffusion for 3D Human Head Synthesis and Editing." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/lan2024eccv-loc3diff/) doi:10.1007/978-3-031-73650-6_4BibTeX
@inproceedings{lan2024eccv-loc3diff,
title = {{Loc3Diff: Local Diffusion for 3D Human Head Synthesis and Editing}},
author = {Lan, Yushi and Tan, Feitong and Xu, Qiangeng and Qiu, Di and Genova, Kyle and Huang, Zeng and Pandey, Rohit and Fanello, Sean and Funkhouser, Thomas and Loy, Chen Change and Zhang, Yinda},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-73650-6_4},
url = {https://mlanthology.org/eccv/2024/lan2024eccv-loc3diff/}
}