MambaStyle：基于状态空间模型的高效StyleGAN反演用于真实图像编辑
MambaStyle: Efficient StyleGAN Inversion for Real Image Editing with State-Space Models
AI总结：
本文提出MambaStyle，一种基于视觉状态空间模型的单阶段编码器方法，用于StyleGAN反演与编辑，在减少参数和计算复杂度的同时，实现了重建质量、编辑效果与效率的优越平衡，适用于实时应用。
摘要：
将真实图像反演到StyleGAN的潜在空间以操纵其属性的任务已被广泛研究。然而，现有的GAN反演方法难以在重建质量、可编辑性和计算效率之间取得平衡。在本文中，我们提出了MambaStyle，一种高效的基于单阶段编码器的GAN反演与编辑方法，利用视觉状态空间模型（VSSMs）来解决这些挑战。具体而言，我们的方法在所提出的架构中集成了VSSMs，与最先进的方法相比，以显著更少的参数和降低的计算复杂度实现了高质量图像反演和灵活编辑。大量实验表明，MambaStyle在反演精度、编辑质量和计算效率之间取得了优越的平衡。值得注意的是，我们的方法以更低的模型复杂度和更快的推理速度实现了优越的反演和编辑结果，使其适用于实时应用。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
