From a single image, GUAVA builds an animatable upper-body 3D Gaussian avatar in one forward pass, using a new hybrid SMPLX/FLAME template and inverse texture mapping, then renders it in real time.
Adversarially-Guided Portrait Matting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present a method for generating alpha mattes using a limited data source. We pretrain a novel transformerbased model (StyleMatte) on portrait datasets. We utilize this model to provide image-mask pairs for the StyleGAN3-based network (StyleMatteGAN). This network is trained unsupervisedly and generates previously unseen imagemask training pairs that are fed back to StyleMatte. We demonstrate that the performance of the matte pulling network improves during this cycle and obtains top results on the human portraits and state-of-the-art metrics on animals dataset. Furthermore, StyleMatteGAN provides high-resolution, privacy-preserving portraits with alpha mattes, making it suitable for various image composition tasks. Our code is available at https://github.com/chroneus/stylematte
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GUAVA: Generalizable Upper Body 3D Gaussian Avatar
From a single image, GUAVA builds an animatable upper-body 3D Gaussian avatar in one forward pass, using a new hybrid SMPLX/FLAME template and inverse texture mapping, then renders it in real time.