Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder

arXiv:2404.04916v1 Announce Type: cross
Abstract: The images produced by diffusion models can attain excellent perceptual quality. However, it is challenging for diffusion models to guarantee distortion, hence the integration of diffusion models and image compression models still needs more comprehensive explorations. This paper presents a diffusion-based image compression method that employs a privileged end-to-end decoder model as correction, which achieves better perceptual quality while guaranteeing the distortion to an extent. We build a diffusion model and design a novel paradigm …

abstract arxiv compression cs.cv cs.lg decoder diffusion diffusion models eess.iv however image images integration paper quality type