4 papers
ViDS: Video Diffusion Shader using 3D Face Tracking
Wenbo Ji, Davide Davoli, Zhe Chen +3
We introduce ViDS, a Video Diffusion Shader that leverages 3D face tracking for expressive and identity-preserving portrait animation. We first reconstruct the identity-specific 3D…
Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image
Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld +3
Neural Parametric Head Models (NPHMs) are a recent advancement over mesh-based 3d morphable models (3DMMs) to facilitate high-fidelity geometric detail. However, fitting NPHMs to v…
SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians
Liam Schoneveld, Zhe Chen, Davide Davoli +4
Accurate, real-time 3D reconstruction of human heads from monocular images and videos underlies numerous visual applications. As 3D ground truth data is hard to come by at scale, p…
GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion
Jiapeng Tang, Davide Davoli, Tobias Kirschstein +2
We propose a novel approach for reconstructing animatable 3D Gaussian avatars from monocular videos captured by commodity devices like smartphones. Photorealistic 3D head avatar re…