Existing multimodal large model-based image compression frameworks often rely on a fragmented integration of semantic retrieval, latent compression, and generative models, resulting in suboptimal performance in both reconstruction fidelity and coding efficiency. To address these challenges, we propose a residual-guided ultra lowrate image compression named ResULIC, which incorporates residual signals into both semantic retrieval and the diffusion-based generation process. Specifically, we introduce Semantic Residual Coding (SRC) to capture the semantic disparity between the original image and its compressed latent representation. A perceptual fidelity optimizer is further applied for superior reconstruction quality. Additionally, we present the Compression-aware Diffusion Model (CDM), which establishes an optimal alignment between bitrates and diffusion time steps, improving compression-reconstruction synergy. Extensive experiments demonstrate the effectiveness of ResULIC, achieving superior objective and subjective performance compared to state-of-the-art diffusion-based methods with - 80.7%, -66.3% BD-rate saving in terms of LPIPS and FID. Project page is available at https: //njuvision.this http URL.
View on arXiv@article{ke2025_2505.08281,
title={ Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion },
author={ Anle Ke and Xu Zhang and Tong Chen and Ming Lu and Chao Zhou and Jiawen Gu and Zhan Ma },
journal={arXiv preprint arXiv:2505.08281},
year={ 2025 }
}