An Edit Friendly DDPM Noise Space: Inversion and Manipulations

arXiv:2304.06140v3 Announce Type: replace-cross
Abstract: Denoising diffusion probabilistic models (DDPMs) employ a sequence of white Gaussian noise samples to generate an image. In analogy with GANs, those noise maps could be considered as the latent code associated with the generated image. However, this native noise space does not possess a convenient structure, and is thus challenging to work with in editing tasks. Here, we propose an alternative latent noise space for DDPM that enables a wide range of editing operations …

arxiv cs.cv cs.lg ddpm edit noise space type