no code implementations • 7 Dec 2023 • Phong Tran, Egor Zakharov, Long-Nhat Ho, Anh Tuan Tran, Liwen Hu, Hao Li
We present a 3D-aware one-shot head reenactment method based on a fully volumetric neural disentanglement framework for source appearance and driver expressions.
1 code implementation • ICCV 2021 • Long-Nhat Ho, Anh Tuan Tran, Quynh Phung, Minh Hoai
In this paper, we eliminate the symmetry requirement with a novel unsupervised algorithm that can learn a 3D reconstruction network from a multi-image dataset.