Enregistré dans:
Détails bibliographiques
Auteurs principaux: Song, Juan, Yang, Lijie, Feng, Mingtao
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.00399
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915551963512832
author Song, Juan
Yang, Lijie
Feng, Mingtao
author_facet Song, Juan
Yang, Lijie
Feng, Mingtao
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2503_00399
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Extremely low-bitrate Image Compression Semantically Disentangled by LMMs from a Human Perception Perspective
Song, Juan
Yang, Lijie
Feng, Mingtao
Computer Vision and Pattern Recognition
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).
title Extremely low-bitrate Image Compression Semantically Disentangled by LMMs from a Human Perception Perspective
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.00399