用耦合随机微分方程实现图像语义编辑，保细节又准达意图。
Semantic Editing with Coupled Stochastic Differential Equations
- 通过相同相关噪声驱动源图与编辑图，同步控制生成过程。
- 编辑后图像在语义上高度匹配提示词，像素级相似性接近原图。
- 无需重训练或额外网络，适用于扩散模型和修正流模型。
使用预训练文本到图像模型编辑图像内容仍具挑战，现有方法常扭曲细节或引入意外伪影。本文提出利用耦合随机微分方程（coupled SDEs）引导任意可通过求解SDE采样的预训练生成模型的采样过程，包括扩散模型和修正流模型。通过让源图像与编辑图像共享相同相关噪声，该方法在保持与源图视觉相似性的同时，使新样本朝向目标语义方向演化。该方法无需重新训练或附加网络，可直接部署，实现高提示词保真度与近乎像素级的一致性。结果表明，耦合SDE是一种简单而强大的可控生成人工智能工具。
原文摘要 · Abstract (English)
Editing the content of an image with a pretrained text-to-image model remains challenging. Existing methods often distort fine details or introduce unintended artifacts. We propose using \emph{coupled stochastic differential equations} (coupled SDEs) to guide the sampling process of any pre-trained generative model that can be sampled by solving an SDE, including diffusion and rectified flow models. By driving both the source image and the edited image with the same correlated noise, our approach steers new samples toward the desired semantics while preserving visual similarity to the source. The method works out-of-the-box, without retraining or auxiliary networks, and achieves high prompt fidelity along with near-pixel-level consistency. These results position coupled SDEs as a simple yet powerful tool for controlled generative AI. Project page: https://z-jianxin.github.io/syncSDE-release/. Code: https://github.com/Z-Jianxin/syncSDE-release.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。