Inpaint4Drag：通过双向变形重用途径，将修复模型应用于基于拖拽的图像编辑

Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping

September 4, 2025

作者: Jingyi Lu, Kai Han

cs.AI

摘要

基于拖拽的图像编辑已成为一种强大的直观图像处理范式。然而，现有方法主要依赖于生成模型的潜在空间操作，导致精度受限、反馈延迟以及模型特定约束。为此，我们提出了Inpaint4Drag，一个将拖拽编辑分解为像素空间双向扭曲与图像修复的新颖框架。受物理世界中弹性物体变形的启发，我们将图像区域视为可变形材料，在用户操作下保持自然形态。我们的方法在512x512分辨率下实现了实时扭曲预览（0.01秒）和高效修复（0.3秒），相比现有方法每次编辑需耗时数分钟，显著提升了交互体验。通过将拖拽输入直接转换为标准修复格式，我们的方法无需修改架构即可作为任何修复模型的通用适配器，自动继承修复技术未来的所有进步。大量实验证明，我们的方法在保持实时性能的同时，实现了卓越的视觉质量和精确控制。项目页面：https://visual-ai.github.io/inpaint4drag/

English

Drag-based image editing has emerged as a powerful paradigm for intuitive image manipulation. However, existing approaches predominantly rely on manipulating the latent space of generative models, leading to limited precision, delayed feedback, and model-specific constraints. Accordingly, we present Inpaint4Drag, a novel framework that decomposes drag-based editing into pixel-space bidirectional warping and image inpainting. Inspired by elastic object deformation in the physical world, we treat image regions as deformable materials that maintain natural shape under user manipulation. Our method achieves real-time warping previews (0.01s) and efficient inpainting (0.3s) at 512x512 resolution, significantly improving the interaction experience compared to existing methods that require minutes per edit. By transforming drag inputs directly into standard inpainting formats, our approach serves as a universal adapter for any inpainting model without architecture modification, automatically inheriting all future improvements in inpainting technology. Extensive experiments demonstrate that our method achieves superior visual quality and precise control while maintaining real-time performance. Project page: https://visual-ai.github.io/inpaint4drag/