# Extremely low-bitrate Image Compression Semantically Disentangled by LMMs from a Human Perception Perspective Source: [Extremely low-bitrate Image Compression Semantically Disentangled by LMMs from a Human Perception Perspective]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:57:13.861Z Authors: Juan Song, Lijie Yang, Mingtao Feng Published: 2025-03-01T08:27:11.000Z ## Abstract It remains a significant challenge to compress images at extremely low bitrate while achieving both semantic consistency and high perceptual quality. Inspired by human progressive perception mechanism, we propose a Semantically Disentangled Image Compression framework (SEDIC) in this paper. Initially, an extremely compressed reference image is obtained through a learned image encoder. Then we leverage LMMs to extract essential semantic components, including overall descriptions, object detailed description, and semantic segmentation masks. We propose a training-free Object Restoration model with Attention Guidance (ORAG) built on pre-trained ControlNet to restore object details conditioned by object-level text descriptions and semantic masks. Based on the proposed ORAG, we design a multistage semantic image decoder to progressively restore the details object by object, starting from the extremely compressed reference image, ultimately generating high-quality and high-fidelity reconstructions. Experimental results demonstrate that SEDIC significantly outperforms state-of-the-art approaches, achieving superior perceptual quality and semantic consistency at extremely low-bitrates ($\\le$ 0.05 bpp). ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()