SAGE self-learns Gaussian expression deformations via joint surfel-SDF optimization and self-supervised consistency, enabling comparable avatar quality from single frames, monocular rotations, or one-shot inputs.
ArXiv abs/2212.08377 (2022)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
GeomHair reconstructs hair strands from colorless 3D scans via orientation estimation from shading and a scan-adapted diffusion prior, while releasing the Strands400 dataset of 400 real-subject reconstructions.
citing papers explorer
-
Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars
SAGE self-learns Gaussian expression deformations via joint surfel-SDF optimization and self-supervised consistency, enabling comparable avatar quality from single frames, monocular rotations, or one-shot inputs.
-
GeomHair: Reconstruction of Hair Strands from Colorless 3D Scans
GeomHair reconstructs hair strands from colorless 3D scans via orientation estimation from shading and a scan-adapted diffusion prior, while releasing the Strands400 dataset of 400 real-subject reconstructions.