Search Results for author:
Found 2 papers, 1 papers with code
VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment
We present a 3D-aware one-shot head reenactment method based on a fully volumetric neural disentanglement framework for source appearance and driver expressions.
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
