The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing

arXiv:2311.01410v2 Announce Type: replace-cross
Abstract: We present a unified probabilistic formulation for diffusion-based image editing, where a latent variable is edited in a task-specific manner and generally deviates from the corresponding marginal distribution induced by the original stochastic or ordinary differential equation (SDE or ODE). Instead, it defines a corresponding SDE or ODE for editing. In the formulation, we prove that the Kullback-Leibler divergence between the marginal distributions of the two SDEs gradually decreases while that for the ODEs remains …

abstract arxiv cs.cv cs.lg differential differential equation diffusion distribution editing equation general image ordinary randomness stochastic type