LazyDrag: 通过显式对应关系在多模态扩散变换器上实现稳定的拖拽编辑
LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence
AI总结：
LazyDrag通过显式对应关系实现多模态扩散变换器的稳定拖拽编辑，消除了隐式点匹配依赖，提升生成能力与精确控制。
摘要：
依赖于通过注意力机制进行隐式点匹配已成为拖拽编辑中的核心瓶颈，导致在削弱的反向强度和昂贵的测试时优化（TTO）之间产生根本性的权衡。这种权衡严重限制了扩散模型的生成能力，抑制了高保真修复和文本引导的创作。在本文中，我们引入了LazyDrag，这是首个针对多模态扩散变换器的拖拽图像编辑方法，直接消除了对隐式点匹配的依赖。具体而言，我们的方法从用户拖拽输入生成显式对应图，作为可靠的参考以增强注意力控制。这种可靠的参考为稳定全强度反向过程打开了可能性，这是拖拽编辑任务中的首次尝试。它消除了对TTO的必要性，并解锁了模型的生成能力。因此，LazyDrag自然地统一了精确的几何控制与文本引导，使之前无法实现的复杂编辑成为可能：打开狗的嘴并修复其内部，生成像“网球”这样的新物体，或者对于模糊的拖拽，做出上下文感知的更改，如将手移动到口袋中。此外，LazyDrag支持多轮工作流，同时进行移动和缩放操作。在DragBench上评估，我们的方法在拖拽准确性和感知质量上优于基线，这通过VIEScore和人工评估得到验证。LazyDrag不仅建立了新的最先进的性能，还开辟了新的编辑范式。
英文摘要：
The reliance on implicit point matching via attention has become a core bottleneck in drag-based editing, resulting in a fundamental compromise on weakened inversion strength and costly test-time optimization (TTO). This compromise severely limits the generative capabilities of diffusion models, suppressing high-fidelity inpainting and text-guided creation. In this paper, we introduce LazyDrag, the first drag-based image editing method for Multi-Modal Diffusion Transformers, which directly eliminates the reliance on implicit point matching. In concrete terms, our method generates an explicit correspondence map from user drag inputs as a reliable reference to boost the attention control. This reliable reference opens the potential for a stable full-strength inversion process, which is the first in the drag-based editing task. It obviates the necessity for TTO and unlocks the generative capability of models. Therefore, LazyDrag naturally unifies precise geometric control with text guidance, enabling complex edits that were previously out of reach: opening the mouth of a dog and inpainting its interior, generating new objects like a ``tennis ball'', or for ambiguous drags, making context-aware changes like moving a hand into a pocket. Additionally, LazyDrag supports multi-round workflows with simultaneous move and scale operations. Evaluated on the DragBench, our method outperforms baselines in drag accuracy and perceptual quality, as validated by VIEScore and human evaluation. LazyDrag not only establishes new state-of-the-art performance, but also paves a new way to editing paradigms.
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。
