FaceLift: Single Image 3D Face Reconstruction
ICCV 2025 | Paper | Code | Project Page
FaceLift transforms a single facial image into a high-fidelity 3D Gaussian head representation. This repository contains the pretrained model checkpoints.
For usage instructions, see the official code repository.
Citation
@misc{lyu2025facelift,
title={FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads},
author={Weijie Lyu and Yi Zhou and Ming-Hsuan Yang and Zhixin Shu},
year={2025},
eprint={2412.17812},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2412.17812}
}
License
Model weights are licensed under the Adobe Research License. See LICENSE for details.
- Downloads last month
- -
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
π
Ask for provider support