Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profile

arXiv:2403.05093v1 Announce Type: new
Abstract: Currently, image generation and synthesis have remarkably progressed with generative models. Despite photo-realistic results, intrinsic discrepancies are still observed in the frequency domain. The spectral discrepancy appeared not only in generative adversarial networks but in diffusion models. In this study, we propose a framework to effectively mitigate the disparity in frequency domain of the generated images to improve generative performance of both GAN and diffusion models. This is realized by spectrum translation for the refinement …

abstract adversarial arxiv cs.cv diffusion diffusion models domain eess.iv filter generative generative adversarial networks generative models image image generation intrinsic networks photo profile results spectrum synthesis translation type