StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN
This simplifies image manipulation for researchers and practitioners by eliminating the need for extra training or models, though it is incremental as it builds on existing StyleGAN capabilities.
The authors tackled the problem of requiring additional architectures or task-specific training for various image manipulation tasks with StyleGAN, showing that using only a pretrained StyleGAN with some operations can perform comparably to state-of-the-art methods on tasks like image blending and panorama generation.
Recently, StyleGAN has enabled various image manipulation and editing tasks thanks to the high-quality generation and the disentangled latent space. However, additional architectures or task-specific training paradigms are usually required for different tasks. In this work, we take a deeper look at the spatial properties of StyleGAN. We show that with a pretrained StyleGAN along with some operations, without any additional architecture, we can perform comparably to the state-of-the-art methods on various tasks, including image blending, panorama generation, generation from a single image, controllable and local multimodal image to image translation, and attributes transfer. The proposed method is simple, effective, efficient, and applicable to any existing pretrained StyleGAN model.