Factorized Diffusion: Perceptual Illusions by Noise Decomposition

arXiv:2404.11615v1 Announce Type: new
Abstract: Given a factorization of an image into a sum of linear components, we present a zero-shot method to control each individual component through diffusion model sampling. For example, we can decompose an image into low and high spatial frequencies and condition these components on different text prompts. This produces hybrid images, which change appearance depending on viewing distance. By decomposing an image into three frequency subbands, we can generate hybrid images with three prompts. We …

abstract arxiv components control cs.cv diffusion diffusion model example factorization image linear low noise prompts sampling spatial sum text through type zero-shot