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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lopez, Jhon, Hinojosa, Carlos, Arguello, Henry, Ghanem, Bernard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909619491700736
author Lopez, Jhon
Hinojosa, Carlos
Arguello, Henry
Ghanem, Bernard
author_facet Lopez, Jhon
Hinojosa, Carlos
Arguello, Henry
Ghanem, Bernard
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15822
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MambaStyle: Efficient StyleGAN Inversion for Real Image Editing with State-Space Models
Lopez, Jhon
Hinojosa, Carlos
Arguello, Henry
Ghanem, Bernard
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
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.
title MambaStyle: Efficient StyleGAN Inversion for Real Image Editing with State-Space Models
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2505.15822