MambaStyle: Efficient StyleGAN Inversion for Real Image Editing with State-Space Models
This work addresses the challenge of balancing reconstruction quality, editability, and efficiency in GAN inversion for real image editing, offering an incremental improvement with reduced computational complexity.
The paper tackles the problem of inverting real images into StyleGAN's latent space for editing by introducing MambaStyle, an efficient encoder-based method using vision state-space models, which achieves high-quality inversion and editing with fewer parameters and faster inference compared to state-of-the-art methods.
The task of inverting real images into StyleGAN's latent space to manipulate their attributes has been extensively studied. However, existing GAN inversion methods struggle to balance high reconstruction quality, effective editability, and computational efficiency. In this paper, we introduce MambaStyle, an efficient single-stage encoder-based approach for GAN inversion and editing that leverages vision state-space models (VSSMs) to address these challenges. Specifically, our approach integrates VSSMs within the proposed architecture, enabling high-quality image inversion and flexible editing with significantly fewer parameters and reduced computational complexity compared to state-of-the-art methods. Extensive experiments show that MambaStyle achieves a superior balance among inversion accuracy, editing quality, and computational efficiency. Notably, our method achieves superior inversion and editing results with reduced model complexity and faster inference, making it suitable for real-time applications.