DirectDrag: 一种高保真、无掩码、无提示的拖动图像编辑方法通过读取引导的特征对齐
DirectDrag: High-Fidelity, Mask-Free, Prompt-Free Drag-based Image Editing via Readout-Guided Feature Alignment
AI总结：
DirectDrag通过读取引导的特征对齐方法实现无掩码、无提示的拖动图像编辑，提升图像质量和拖动精度。
摘要：
基于生成模型的拖动图像编辑提供了对图像结构的直观控制。然而，现有方法严重依赖于手动提供的掩码和文本提示以保持语义保真度和运动精度。去除这些约束条件会带来根本性的权衡：没有掩码就会产生视觉伪影，没有提示就会导致空间控制不佳。为了解决这些限制，我们提出了DirectDrag，一种新的无掩码和无提示的编辑框架。DirectDrag能够以精确和高效的方式进行操作，同时在最小的用户输入下保持高图像保真度和准确的点对齐。DirectDrag引入了两个关键创新。首先，我们设计了一个自动软掩码生成模块，该模块能够智能地从点位移中推断出可编辑区域，自动沿运动路径局部化变形，同时通过生成模型的固有能力保持上下文完整性。其次，我们开发了一种读取引导的特征对齐机制，该机制利用中间扩散激活来在点编辑过程中保持结构一致性，显著提高了视觉保真度。尽管在没有手动掩码或提示的情况下运行，DirectDrag在图像质量上优于现有方法，同时保持了具有竞争力的拖动精度。在DragBench和现实世界场景中的大量实验展示了DirectDrag在高质量、交互式图像编辑中的有效性和实用性。项目页面：https://frakw.github.io/DirectDrag/。代码可在：https://github.com/frakw/DirectDrag。
英文摘要：
Drag-based image editing using generative models provides intuitive control over image structures. However, existing methods rely heavily on manually provided masks and textual prompts to preserve semantic fidelity and motion precision. Removing these constraints creates a fundamental trade-off: visual artifacts without masks and poor spatial control without prompts. To address these limitations, we propose DirectDrag, a novel mask- and prompt-free editing framework. DirectDrag enables precise and efficient manipulation with minimal user input while maintaining high image fidelity and accurate point alignment. DirectDrag introduces two key innovations. First, we design an Auto Soft Mask Generation module that intelligently infers editable regions from point displacement, automatically localizing deformation along movement paths while preserving contextual integrity through the generative model's inherent capacity. Second, we develop a Readout-Guided Feature Alignment mechanism that leverages intermediate diffusion activations to maintain structural consistency during point-based edits, substantially improving visual fidelity. Despite operating without manual mask or prompt, DirectDrag achieves superior image quality compared to existing methods while maintaining competitive drag accuracy. Extensive experiments on DragBench and real-world scenarios demonstrate the effectiveness and practicality of DirectDrag for high-quality, interactive image manipulation. Project Page: https://frakw.github.io/DirectDrag/. Code is available at: https://github.com/frakw/DirectDrag.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
