Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior

arXiv:2404.18820v1 Announce Type: cross
Abstract: Compressing images at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. Existing extreme image compression methods generally suffer from heavy compression artifacts or low-fidelity reconstructions. To address this problem, we propose a novel extreme image compression framework that combines compressive VAEs and pre-trained text-to-image diffusion models in an end-to-end manner. Specifically, we introduce a latent feature-guided compression module based on compressive VAEs. This module compresses …

abstract arxiv challenge compression cs.cv diffusion eess.iv feature fidelity guidance image images information loss low novel per pixel prior type