pith. sign in

arxiv: 2312.11396 · v2 · pith:S5PMB47Enew · submitted 2023-12-18 · 💻 cs.CV · cs.AI

MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance

classification 💻 cs.CV cs.AI
keywords editingcomplexlocalizedscenariosimagemag-editmask-basedalignment
0
0 comments X
read the original abstract

Recent diffusion-based image editing approaches have exhibited impressive editing capabilities in images with simple compositions. However, localized editing in complex scenarios has not been well-studied in the literature, despite its growing real-world demands. Existing mask-based inpainting methods fall short of retaining the underlying structure within the edit region. Meanwhile, mask-free attention-based methods often exhibit editing leakage and misalignment in more complex compositions. In this work, we develop MAG-Edit, a training-free, inference-stage optimization method, which enables localized image editing in complex scenarios. In particular, MAG-Edit optimizes the noise latent feature in diffusion models by maximizing two mask-based cross-attention constraints of the edit token, which in turn gradually enhances the local alignment with the desired prompt. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method in achieving both text alignment and structure preservation for localized editing within complex scenarios.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Rethinking Scribble-Guided Image Editing: Generalization, Instruction Adherence, and Multi-Tasking

    cs.CV 2026-05 unverdicted novelty 6.0

    Empirical studies reveal instruction-level generalization as the main bottleneck in scribble-guided editing; three strategies (curriculum, multi-task mosaicking, edit-focused loss) achieve SOTA on VIBE benchmark.