We present UniMIC, a universal multi-modality image compression framework, intending to unify the rate-distortion-perception (RDP) optimization for multiple image codecs simultaneously through excavating cross-modality generative priors. Unlike most existing works that need to design and optimize image codecs from scratch, our UniMIC introduces the visual codec repository, which incorporates amounts of representative image codecs and directly uses them as the basic codecs for various practical applications. Moreover, we propose multi-grained textual coding, where variable-length content prompt and compression prompt are designed and encoded to assist the perceptual reconstruction through the multi-modality conditional generation. In particular, a universal perception compensator is proposed to improve the perception quality of decoded images from all basic codecs at the decoder side by reusing text-assisted diffusion priors from stable diffusion. With the cooperation of the above three strategies, our UniMIC achieves a significant improvement of RDP optimization for different compression codecs, e.g., traditional and learnable codecs, and different compression costs, e.g., ultra-low bitrates. The code will be available in https://github.com/Amygyx/UniMIC .
@article{arxiv.2412.04912,
title = {UniMIC: Towards Universal Multi-modality Perceptual Image Compression},
author = {Yixin Gao and Xin Li and Xiaohan Pan and Runsen Feng and Zongyu Guo and Yiting Lu and Yulin Ren and Zhibo Chen},
journal= {arXiv preprint arXiv:2412.04912},
year = {2024}
}