Adversarially-Guided Portrait Matting
This work addresses the need for high-resolution, privacy-preserving portrait matting for image composition tasks, but it is incremental as it builds on existing transformer and GAN methods.
The paper tackles the problem of generating alpha mattes for portraits with limited data by using a transformer-based model and a StyleGAN3-based network in a cyclic training process, achieving top results on human portraits and state-of-the-art metrics on an animals dataset.
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