MambaStyle: Efficient StyleGAN Inversion for Real Image Editing with State-Space Models

TL;DR

MambaStyle introduces a novel, efficient encoder-based GAN inversion method using vision state-space models, achieving high-quality image reconstruction and editing with reduced complexity suitable for real-time applications.

Contribution

The paper proposes MambaStyle, a single-stage encoder approach leveraging VSSMs for improved GAN inversion and editing efficiency, balancing quality and computational cost.

Findings

Achieves superior inversion and editing quality

Reduces model complexity and inference time

Suitable for real-time image editing applications

Abstract

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.