Feature-Style Encoder for Style-Based GAN Inversion
This addresses the challenge of accurate and fast image and video editing using GANs, representing an incremental improvement over prior inversion techniques.
The paper tackles the problem of inverting real images into the latent space of style-based GANs for editing, achieving better perceptual quality and lower reconstruction error than existing methods, with state-of-the-art results across multiple data domains.
We propose a novel architecture for GAN inversion, which we call Feature-Style encoder. The style encoder is key for the manipulation of the obtained latent codes, while the feature encoder is crucial for optimal image reconstruction. Our model achieves accurate inversion of real images from the latent space of a pre-trained style-based GAN model, obtaining better perceptual quality and lower reconstruction error than existing methods. Thanks to its encoder structure, the model allows fast and accurate image editing. Additionally, we demonstrate that the proposed encoder is especially well-suited for inversion and editing on videos. We conduct extensive experiments for several style-based generators pre-trained on different data domains. Our proposed method yields state-of-the-art results for style-based GAN inversion, significantly outperforming competing approaches. Source codes are available at https://github.com/InterDigitalInc/FeatureStyleEncoder .