HairCUP trains a universal 3D avatar prior with separately modeled face and hair, using synthetic bald images, enabling hairstyle swapping and few-shot personalization.
Preface: A data-driven volumetric prior for few-shot ultra high-resolution face synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars
HairCUP trains a universal 3D avatar prior with separately modeled face and hair, using synthetic bald images, enabling hairstyle swapping and few-shot personalization.