Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping
This work addresses the need for more intuitive and efficient image editing tools for users, though it is incremental as it builds on existing inpainting models.
The paper tackled the problem of limited precision and slow feedback in drag-based image editing by introducing Inpaint4Drag, a framework that uses bidirectional warping and inpainting to achieve real-time warping previews (0.01s) and efficient inpainting (0.3s) at 512x512 resolution.
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/