CLIPortrait disentangles camera and geometry information from CLIP embeddings via 2D canonicalization, then prevents distribution collapse with a Jacobian regularizer, enabling text-guided 3D portrait generation from unlabeled 2D data.
Bergman, Petr Kellnhofer, Yifan Wang, Eric R
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
-
Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation
CLIPortrait disentangles camera and geometry information from CLIP embeddings via 2D canonicalization, then prevents distribution collapse with a Jacobian regularizer, enabling text-guided 3D portrait generation from unlabeled 2D data.