Consistent-Inversion: 用于结构保持视觉编辑的反向一致性引导
Consistent-Inversion: Reverse Consistency Guidance for Structure-Preserving Visual Editing
AI总结：
提出Consistent-Inversion，一种无训练的反向一致性引导框架，通过检查中间目标轨迹能否在源提示下反向到源反转轨迹，并利用反向一致性差异校正早期去噪步骤，在保持结构的同时提升编辑效果。
摘要：
文本引导的扩散模型已成为真实图像视觉编辑的有效工具，其中编辑后的图像必须遵循目标指令，同时保持与编辑无关的结构。大多数无训练编辑器依赖于反转：源图像被映射到一个噪声潜变量轨迹，终端潜变量被重新用于目标提示去噪。这种重用有助于保持结构，但也耦合了源重建和目标编辑。由此产生的轨迹不匹配可能会损害背景/布局细节，或过度约束预期编辑。本文提出Consistent-Inversion，一种用于结构保持视觉编辑的无训练反向一致性引导框架。Consistent-Inversion不将反转后的源潜变量视为固定初始化，而是检查中间目标轨迹是否能在源提示下反向到源反转轨迹。为使这一检查明确，我们构建了一个辅助的目标侧噪声表示，执行源引导的反向去噪，并将得到的反向一致性差异作为校正信号，用于选定的早期目标去噪步骤。该方法不更新模型参数，与基于反转的编辑器兼容，且在稀疏应用时仅引入少量推理开销。在PIE-Bench上的实验表明，Consistent-Inversion在统一的SD3.5协议下提高了背景和结构保真度，同时保持目标提示对齐，兼容性实验进一步验证了相同校正原则在经典Stable-Diffusion反转流水线上的有效性。
英文摘要：
Text-guided diffusion models have become effective tools for real-image visual editing, where the edited image must follow a target instruction while preserving editing-irrelevant structure. Most training-free editors rely on inversion: a source image is mapped to a noisy latent trajectory and the terminal latent is reused for target-prompt denoising. This reuse is useful for preservation, but it also couples source reconstruction and target editing. The resulting trajectory mismatch may either damage background/layout details or over-constrain the intended edit. This paper presents Consistent-Inversion, a training-free reverse consistency guidance framework for structure-preserving visual editing. Instead of treating the inverted source latent as a fixed initialization, Consistent-Inversion checks whether an intermediate target trajectory can be reversed toward the source inversion trajectory under the source prompt. To make this check well-defined, we construct an auxiliary target-side noise representation, perform source-guided reverse denoising, and use the resulting reverse consistency discrepancy as a correction signal for selected early target denoising steps. The method does not update model parameters, is compatible with inversion-based editors, and introduces only a small inference overhead when applied sparsely. Experiments on PIE-Bench show that Consistent-Inversion improves background and structural fidelity under a unified SD3.5 protocol while maintaining target-prompt alignment, and compatibility experiments further verify the same correction principle on classical Stable-Diffusion inversion pipelines.
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。
