解决扩散模型逆向生成中噪声不自然的问题，提升图像编辑效果。
SSI-DM: Singularity Skipping Inversion of Diffusion Models
- 跳过数学奇异区域，先加小噪再标准反演，改善噪声分布。
- 逆向生成的噪声呈自然高斯分布，重建精度高且可编辑性强。
- 无需修改模型，通用性强，适合各类扩散模型图像编辑任务。
将真实图像逆向映射到噪声空间是利用扩散模型进行图像编辑的关键步骤，但现有方法在早期加噪阶段因精度不足，导致生成非高斯噪声且编辑性差。我们识别出根本原因：数学上的奇异性使逆向过程本质上病态。为此提出奇异点跳过反演方法（SSI-DM），通过在标准反演前添加微小噪声，绕过该奇异区域。该简单策略使逆向噪声具备自然高斯特性，同时保持高重建保真度。作为通用插件式技术，该方法在公开图像数据集上于重建与插值任务中均表现更优，为扩散模型逆向提供了原理清晰、高效可靠的解决方案。
原文摘要 · Abstract (English)
Inverting real images into the noise space is essential for editing tasks using diffusion models, yet existing methods produce non-Gaussian noise with poor editability due to the inaccuracy in early noising steps. We identify the root cause: a mathematical singularity that renders inversion fundamentally ill-posed. We propose Singularity Skipping Inversion of Diffusion Models (SSI-DM), which bypasses this singular region by adding small noise before standard inversion. This simple approach produces inverted noise with natural Gaussian properties while maintaining reconstruction fidelity. As a plug-and-play technique compatible with general diffusion models, our method achieves superior performance on public image datasets for reconstruction and interpolation tasks, providing a principled and efficient solution to diffusion model inversion.
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。