Diffusion Model Inversion
Overview
Diffusion model inversion works backward from an image, audio recording, or other observation to estimate the noise or trajectory that a diffusion or flow model can use to reproduce it. Approaches include DDIM and ODE/SDE inversion, fixed-point and gradient-based optimization, and trajectory or timestep corrections; some methods also recover prompts or optimize the starting noise. Inversion supports text-guided editing, image restoration and reconstruction, watermark detection, and scientific inverse problems, with evaluations often measuring reconstruction fidelity, edit alignment, and preservation of unchanged regions on benchmarks such as PIE-Bench. A central tension is that a close reconstruction does not necessarily mean the original latent was recovered accurately, while stronger guidance or edits can reduce fidelity and structural preservation.
Latest papers
37 papers2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.