AI RESEARCH
SSI-DM: Singularity Skipping Inversion of Diffusion Models
arXiv CS.CV
•
ArXi:2602.02193v2 Announce Type: replace 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.