English

Rethinking Structure Preservation in Text-Guided Image Editing with Visual Autoregressive Models

Computer Vision and Pattern Recognition 2026-03-31 v1

Abstract

Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image editing. By shifting the editing paradigm from noise manipulation in diffusion-based methods to token-level operations, VAR-based approaches achieve better background preservation and significantly faster inference. However, existing VAR-based editing methods still face two key challenges: accurately localizing editable tokens and maintaining structural consistency in the edited results. In this work, we propose a novel text-guided image editing framework rooted in an analysis of intermediate feature distributions within VAR models. First, we introduce a coarse-to-fine token localization strategy that can refine editable regions, balancing editing fidelity and background preservation. Second, we analyze the intermediate representations of VAR models and identify structure-related features, by which we design a simple yet effective feature injection mechanism to enhance structural consistency between the edited and source images. Third, we develop a reinforcement learning-based adaptive feature injection scheme that automatically learns scale- and layer-specific injection ratios to jointly optimize editing fidelity and structure preservation. Extensive experiments demonstrate that our method achieves superior structural consistency and editing quality compared with state-of-the-art approaches, across both local and global editing scenarios.

Keywords

Cite

@article{arxiv.2603.28367,
  title  = {Rethinking Structure Preservation in Text-Guided Image Editing with Visual Autoregressive Models},
  author = {Tao Xia and Jiawei Liu and Yukun Zhang and Ting Liu and Wei Wang and Lei Zhang},
  journal= {arXiv preprint arXiv:2603.28367},
  year   = {2026}
}
R2 v1 2026-07-01T11:44:01.705Z