TweezeEdit: 通过路径正则化实现一致且高效的图像编辑
TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
AI总结：
TweezeEdit通过路径正则化实现高效一致的图像编辑，无需调优和倒置，提升语义保留和实时性能。
摘要：
大规模预训练的扩散模型使用户能够通过文本引导编辑图像。然而，现有方法往往过度对齐目标提示，而无法充分保留源图像的语义。此类方法通过源图像的倒置噪声生成目标图像，称为倒置锚点。我们发现这种策略在语义保留和效率上均不理想。我们提出了TweezeEdit，一种无需调优和倒置的框架，用于一致且高效的图像编辑。我们的方法通过正则化整个去噪路径，而不是仅依赖倒置锚点，确保源语义的保留并缩短编辑路径。通过梯度驱动的正则化，我们利用一致性模型在直接路径上高效地注入目标提示语义。大量实验表明，TweezeEdit在语义保留和目标对齐方面表现优异，优于现有方法。值得注意的是，它仅需12步（每编辑1.6秒），凸显了其在实时应用中的潜力。
英文摘要：
Large-scale pre-trained diffusion models empower users to edit images through text guidance. However, existing methods often over-align with target prompts while inadequately preserving source image semantics. Such approaches generate target images explicitly or implicitly from the inversion noise of the source images, termed the inversion anchors. We identify this strategy as suboptimal for semantic preservation and inefficient due to elongated editing paths. We propose TweezeEdit, a tuning- and inversion-free framework for consistent and efficient image editing. Our method addresses these limitations by regularizing the entire denoising path rather than relying solely on the inversion anchors, ensuring source semantic retention and shortening editing paths. Guided by gradient-driven regularization, we efficiently inject target prompt semantics along a direct path using a consistency model. Extensive experiments demonstrate TweezeEdit's superior performance in semantic preservation and target alignment, outperforming existing methods. Remarkably, it requires only 12 steps (1.6 seconds per edit), underscoring its potential for real-time applications.
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。
