Zippo: Zipping Color and Transparency Distributions into a Single Diffusion Model

arXiv:2403.11077v1 Announce Type: new
Abstract: Beyond the superiority of the text-to-image diffusion model in generating high-quality images, recent studies have attempted to uncover its potential for adapting the learned semantic knowledge to visual perception tasks. In this work, instead of translating a generative diffusion model into a visual perception model, we explore to retain the generative ability with the perceptive adaptation. To accomplish this, we present Zippo, a unified framework for zipping the color and transparency distributions into a single …

abstract arxiv beyond color cs.cv diffusion diffusion model generative image image diffusion images knowledge perception quality semantic studies tasks text text-to-image transparency type visual work